Michal Valko

148
Documents
Affiliations actuelles
  • Institut National de Recherche en Informatique et en Automatique (Inria)
  • Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay)
  • DeepMind [Paris]
  • Meta AI Research [Paris]
Contact

Présentation

Michal is the Founding Researcher at a stealth startup, tenured researcher at Inria, and a lecturer at MVA at ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. He works on methods and settings that are able to deal with minimal feedback, such as deep reinforcement learning, bandit algorithms, self-supervised learning, or self play. Michal has recently worked on representation learning, world models and deep (reinforcement) learning algorithms that have some theoretical underpinning. In the past he has also worked on sequential algorithms with structured decisions where exploiting the structure leads to provably faster learning. Michal is now working on a new generation of large language models (LLMs), in addition to providing algorithmic solutions for their scalable test-time inference, fine-tuning and alignment. He received his PhD in 2011 from the University of Pittsburgh, before getting a tenure at Inria in 2012 and co-creating Google DeepMind Paris with R. Munos. In 2024, he became a Principal Llama Scientist at Meta, building online reinforcement learning stack and research for Llama 3.

Domaines de recherche

Machine Learning [stat.ML]

Publications

Publications

Image document

The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback

Côme Fiegel , Pierre Menard , Tadashi Kozuno , Michal Valko , Vianney Perchet
ICML 2025 - 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada
Communication dans un congrès hal-05234074 v1
Image document

Demonstration-Regularized RL

Daniil Tiapkin , Denis Belomestny , Daniele Calandriello , Eric Moulines , Alexey Naumov et al.
The Twelfth International Conference on Learning Representations, May 2024, Vienne, Austria. ⟨10.48550/arXiv.2310.17303⟩
Communication dans un congrès hal-05155159 v1
Image document

Generalized preference optimization: A unified approach to offline alignment

Yunhao Tang , Zhaohan Daniel Guo , Zeyu Zheng , Daniele Calandriello , Rémi Munos et al.
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria
Communication dans un congrès hal-05413273 v1
Image document

Unlocking the power of representations in long-term novelty-based exploration

Alaa Saade , Steven Kapturowski , Daniele Calandriello , Charles Blundell , Pablo Sprechmann et al.
ICLR 2024 - 12th International Conference on Learning Representations, May 2024, Vienna, Austria
Communication dans un congrès hal-05413278 v1

rlberry - A Reinforcement Learning Library for Research and Education

Domingues, Omar Darwiche , Flet-Berliac, Yannis , Leurent, Edouard , Ménard, Pierre , Shang, Xuedong et al.
Machine Learning Conference, Jan 2024, Online, United States
Communication dans un congrès hal-05437168 v1
Image document

Human alignment of large language models through online preference optimisation

Daniele Calandriello , Daniel Guo , Rémi Munos , Mark Rowland , Yunhao Tang et al.
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria
Communication dans un congrès hal-05413272 v1
Image document

A general theoretical paradigm to understand learning from human preferences

Mohammad Gheshlaghi Azar , Mark Rowland , Bilal Piot , Zhaohan Daniel Guo , Daniele Calandriello et al.
AISTATS 2024 - 27th International Conference on Artificial Intelligence and Statistics, May 2024, Valencia, Spain
Communication dans un congrès hal-05413277 v1
Image document

Decoding-time realignment of language models

Tianlin Liu , Shangmin Guo , Leonardo Bianco , Daniele Calandriello , Quentin Berthet et al.
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria
Communication dans un congrès hal-05413275 v1
Image document

Metacognitive capabilities of LLMs: An exploration in mathematical problem solving

Aniket Didolkar , Anirudh Goyal , Nan Rosemary Ke , Siyuan Guo , Michal Valko et al.
NeurIPS 2024 - Annual Conference on Neural Information Processing Systems, Dec 2024, Vancouver, Canada
Communication dans un congrès hal-05413270 v1
Image document

Nash learning from human feedback

Rémi Munos , Michal Valko , Daniele Calandriello , Mohammad Gheshlaghi Azar , Mark Rowland et al.
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria
Communication dans un congrès hal-05413271 v1
Image document

DoMo-AC: Doubly multi-step off-policy actor-critic algorithm

Yunhao Tang , Tadashi Kozuno , Mark Rowland , Anna Harutyunyan , Rémi Munos et al.
ICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413282 v1
Image document

Model-free Posterior Sampling via Learning Rate Randomization

Daniil Tiapkin , Denis Belomestny , Daniele Calandriello , Eric Moulines , Remi Munos et al.
Advances in Neural Information Processing Systems 36 (NeurIPS 2023), Dec 2023, New Orleans, United States. ⟨10.48550/arXiv.2310.18186⟩
Communication dans un congrès hal-05155164 v1
Image document

Understanding self-predictive learning for reinforcement learning

Yunhao Tang , Zhaohan Daniel Guo , Pierre Harvey Richemond , Bernardo Ávila Pires , Yash Chandak et al.
ICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413281 v1
Image document

Quantile credit assignment

Thomas Mesnard , Wenqi Chen , Alaa Saade , Yunhao Tang , Mark Rowland et al.
International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413308 v1
Image document

Curiosity in hindsight: Intrinsic exploration in stochastic environments

Daniel Jarrett , Corentin Tallec , Florent Altché , Thomas Mesnard , Rémi Munos et al.
ICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413279 v1
Image document

Regularization and variance-weighted regression achieves minimax optimality in linear MDPs: Theory and practice

Toshinori Kitamura , Tadashi Kozuno , Yunhao Tang , Nino Vieillard , Michal Valko et al.
ICML 2023 - International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413283 v1
Image document

Half-Hop: A graph upsampling approach for slowing down message passing

Mehdi Azabou , Venkataramana Ganesh , Shantanu Thakoor , Chi-Heng Lin , Lakshmi Sathidevi et al.
ICML 2023 - 40 th International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413309 v1

VA-learning as a more efficient alternative to Q-learning

Yunhao Tang , Rémi Munos , Mark Rowland , Michal Valko
International Conference on Machine Learning, Jul 2023, Honolulu, United States
Communication dans un congrès hal-05413306 v1
Image document

From Dirichlet to Rubin: Optimistic exploration in RL without bonuses

Daniil Tiapkin , Denis Belomestny , Éric Moulines , Alexey Naumov , Sergey Samsonov et al.
ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, United States
Communication dans un congrès hal-05413310 v1
Image document

Retrieval-augmented reinforcement learning

Anirudh Goyal , Abram L Friesen , Theophane Weber , Andrea Banino , Nan Rosemary Ke et al.
International Conference on Machine Learning, Jul 2022, Baltimore, United States
Communication dans un congrès hal-05413311 v1
Image document

BYOL-Explore: Exploration by bootstrapped prediction

Zhaohan Daniel Guo , Shantanu Thakoor , Miruna Pîslar , Bernardo Ávila Pires , Florent Altché et al.
NeurIPS 2022 - 36th International Conference on Neural Information Processing Systems, Nov 2022, New Orleans, United States
Communication dans un congrès hal-05413284 v1
Image document

Scaling Gaussian process optimization by evaluating a few unique candidates multiple times

Daniele Calandriello , Luigi Carratino , Alessandro Lazaric , Michal Valko , Lorenzo Rosasco
International Conference on Machine Learning, Jul 2022, Baltimore, United States
Communication dans un congrès hal-05413313 v1
Image document

Large-scale representation learning on graphs via bootstrapping

Shantanu Thakoor , Corentin Tallec , Mohammad Gheshlaghi Azar , Mehdi Azabou , Eva L. Dyer et al.
International Conference on Learning Representations, Apr 2022, Virtual, United States
Communication dans un congrès hal-05413315 v1
Image document

Marginalized operators for off-policy reinforcement learning

Yunhao Tang , Mark Rowland , Rémi Munos , Michal Valko
AISTATS 2022 - 25th International Conference on Artifi- cial Intelligence and Statistics, Mar 2022, Virtual, Spain
Communication dans un congrès hal-05413316 v1
Image document

Adaptive multi-goal exploration

Jean Tarbouriech , Omar Darwiche Domingues , Pierre Ménard , Matteo Pirotta , Michal Valko et al.
AISTATS 2022 - 25th International Conference on Artifi- cial Intelligence and Statistic, Mar 2022, Virtual, Spain
Communication dans un congrès hal-05413285 v1
Image document

Kernel-based reinforcement Learning: A finite-time analysis

Omar D Domingues , Pierre Ménard , Matteo Pirotta , Emilie Kaufmann , Michal Valko
International Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria
Communication dans un congrès hal-02541790 v2
Image document

Drop, Swap, and Generate: A self-supervised approach for generating neural activity

Ran Liu , Mehdi Azabou , Max Dabagia , Chi-Heng Lin , Mohammad Gheshlaghi Azar et al.
Neural Information Processing Systems, Dec 2021, Virtual, United States
Communication dans un congrès hal-05413317 v1
Image document

Fast active learning for pure exploration in reinforcement learning

Pierre Ménard , Omar Darwiche Domingues , Emilie Kaufmann , Anders Jonsson , Edouard Leurent et al.
International Conference on Machine Learning, Jul 2021, Vienna, Austria
Communication dans un congrès hal-02906985 v3
Image document

Mine Your Own vieW: Self-supervised learning through across-sample prediction

Mehdi Azabou , Mohammad Gheshlaghi Azar , Ran Liu , Chi-Heng Lin , Erik C. Johnson et al.
ICML 2021 - The 38th International Conference on Machine Learning, Jan 2021, Online, United States
Communication dans un congrès hal-05413288 v1
Image document

Unifying gradient estimators for meta-reinforcement learning via off-policy evaluation

Yunhao Tang , Tadashi Kozuno , Mark Rowland , Rémi Munos , Michal Valko
Neural Information Processing Systems, Dec 2021, Virtual, United States
Communication dans un congrès hal-05413286 v1
Image document

Online A-optimal design and active linear regression

Xavier Fontaine , Pierre Perrault , Michal Valko , Vianney Perchet
International Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria. ⟨10.48550/arXiv.1906.08509⟩
Communication dans un congrès hal-03289318 v1
Image document

Episodic reinforcement learning in finite MDPs: Minimax lower bounds revisited

Omar Darwiche Domingues , Pierre Ménard , Emilie Kaufmann , Michal Valko
Algorithmic Learning Theory, Mar 2021, Paris / Virtual, France
Communication dans un congrès hal-03289004 v1
Image document

Revisiting Peng's Q(λ) for for modern reinforcement learning

Tadashi Kozuno , Yunhao Tang , Mark Rowland , Rémi Munos , Steven Kapturowski et al.
International Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria
Communication dans un congrès hal-03289292 v1
Image document

Model-free learning for two-player zero-sum partially observable Markov games with perfect recall

Tadashi Kozuno , Pierre Ménard , Rémi Munos , Michal Valko
Neural Information Processing Systems, Dec 2021, Virtual, United States
Communication dans un congrès hal-05413318 v1
Image document

Broaden your views for self-supervised video learning

Adrià Recasens , Pauline Luc , Jean-Baptiste Alayrac , Luyu Wang , Florian Strub et al.
IEEE/CVF International Conference on Computer Vision, Oct 2021, Virtual, Canada
Communication dans un congrès hal-05413319 v1
Image document

A kernel-based approach to non-stationary reinforcement learning in metric spaces

Omar D Domingues , Pierre Ménard , Matteo Pirotta , Emilie Kaufmann , Michal Valko
International Conference on Artificial Intelligence and Statistics, Apr 2021, San Diego / Virtual, United States
Communication dans un congrès hal-03289026 v1
Image document

Sample complexity bounds for stochastic shortest path with a generative model

Jean Tarbouriech , Matteo Pirotta , Michal Valko , Alessandro Lazaric
Algorithmic Learning Theory, 2021, Paris, France
Communication dans un congrès hal-03288988 v1
Image document

Taylor expansion of discount factors

Yunhao Tang , Mark Rowland , Rémi Munos , Michal Valko
International Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria
Communication dans un congrès hal-03289295 v1
Image document

UCB Momentum Q-learning: Correcting the bias without forgetting

Pierre Ménard , Omar Darwiche Domingues , Xuedong Shang , Michal Valko
International Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria
Communication dans un congrès hal-03289033 v1
Image document

Density-based bonuses on learned representations for reward-free exploration in deep reinforcement learning

Omar Darwiche Domingues , Corentin Tallec , Rémi Munos , Michal Valko
ICML 2021 - The 38th International Conference on Machine Learning, Jan 2021, Online, United States
Communication dans un congrès hal-05413290 v1
Image document

Adaptive reward-free exploration

Emilie Kaufmann , Pierre Ménard , Omar Darwiche Domingues , Anders Jonsson , Edouard Leurent et al.
Algorithmic Learning Theory, 2021, Paris, France
Communication dans un congrès hal-02864574 v1
Image document

Gamification of pure exploration for linear bandits

Rémy Degenne , Pierre Ménard , Xuedong Shang , Michal Valko
ICML 2020 - International Conference on Machine Learning, Aug 2020, Vienna / Virtual, Austria
Communication dans un congrès hal-02884330 v1
Image document

Sampling from a k-DPP without looking at all items

Daniele Calandriello , Michał Dereziński , Michal Valko
Neural Information Processing Systems, 2020, Montréal, Canada
Communication dans un congrès hal-03287832 v1
Image document

Fixed-confidence guarantees for Bayesian best-arm identification

Xuedong Shang , Rianne de Heide , Emilie Kaufmann , Pierre Ménard , Michal Valko
International Conference on Artificial Intelligence and Statistics, 2020, Palermo, Italy
Communication dans un congrès hal-02330187 v2
Image document

No-regret exploration in goal-oriented reinforcement learning

Jean Tarbouriech , Evrard Garcelon , Michal Valko , Matteo Pirotta , Alessandro Lazaric
International Conference on Machine Learning, 2020, Vienna / Virtual, Austria
Communication dans un congrès hal-03287824 v1
Image document

Derivative-free & order-robust optimisation

Victor Gabillon , Rasul Tutunov , Michal Valko , Haitham Bou Ammar
International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo / Virtual, Italy
Communication dans un congrès hal-03288939 v1
Image document

Monte-Carlo tree search as regularized policy optimization

Jean-Bastien Grill , Florent Altché , Yunhao Tang , Thomas Hubert , Michal Valko et al.
International Conference on Machine Learning, 2020, Vienna, Austria
Communication dans un congrès hal-02950136 v1
Image document

Bootstrap Your Own Latent: A new approach to self-supervised learning

Jean-Bastien Grill , Florian Strub , Florent Altché , Corentin Tallec , Pierre H Richemond et al.
Neural Information Processing Systems, 2020, Montréal, Canada
Communication dans un congrès hal-02869787 v2
Image document

Near-linear time Gaussian process optimization with adaptive batching and resparsification

Daniele Calandriello , Luigi Carratino , Alessandro Lazaric , Michal Valko , Lorenzo Rosasco
International Conference on Machine Learning, 2020, Vienna, Austria
Communication dans un congrès hal-02950066 v1
Image document

Covariance-adapting algorithm for semi-bandits with application to sparse outcomes

Pierre Perrault , Vianney Perchet , Michal Valko
Conference on Learning Theory, 2020, Graz, Austria
Communication dans un congrès hal-02876102 v1
Image document

Taylor expansion policy optimization

Yunhao Tang , Michal Valko , Rémi Munos
International Conference on Machine Learning, 2020, Vienna, Austria
Communication dans un congrès hal-02509561 v1
Image document

Adaptive multi-fidelity optimization with fast learning rates

Côme Fiegel , Victor Gabillon , Michal Valko
International Conference on Artificial Intelligence and Statistics, 2020, Palermo, Italy
Communication dans un congrès hal-03288879 v1
Image document

Statistical efficiency of Thompson sampling for combinatorial semi-bandits

Pierre H Richemond , Jean-Bastien Grill , Florent Altché , Corentin Tallec , Florian Strub et al.
Neural Information Processing Systems Conference, Dec 2020, Virtual, France
Communication dans un congrès hal-03288983 v1
Image document

Planning in Markov Decision Processes with Gap-Dependent Sample Complexity

Anders Jonsson , Emilie Kaufmann , Pierre Ménard , Omar D Domingues , Edouard Leurent et al.
Neural Information Processing Systems, 2020, Vancouver, France
Communication dans un congrès hal-02863486 v2
Image document

A single algorithm for both restless and rested rotting bandits

Julien Seznec , Pierre Menard , Alessandro Lazaric , Michal Valko
International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo / Virtual, Italy
Communication dans un congrès hal-03287835 v1
Image document

Stochastic bandits with arm-dependent delays

Anne Gael Manegueu , Claire Vernade , Alexandra Carpentier , Michal Valko
International Conference on Machine Learning, 2020, Vienna, Austria
Communication dans un congrès hal-02950116 v1
Image document

Reward-free exploration beyond finite-horizon

Jean Tarbouriech , Matteo Pirotta , Michal Valko , Alessandro Lazaric
ICML 2020 Workshop on Theoretical Foundations of Reinforcement Learning, 2020, Vienna, France
Communication dans un congrès hal-03288970 v1
Image document

Budgeted online influence maximization

Pierre Perrault , Jennifer Healey , Zheng Wen , Michal Valko
International Conference on Machine Learning, 2020, Vienna, Austria
Communication dans un congrès hal-02904278 v1
Image document

Improved sample complexity for incremental autonomous exploration in MDPs

Jean Tarbouriech , Matteo Pirotta , Michal Valko , Alessandro Lazaric
Neural Information Processing Systems, 2020, Montréal, Canada
Communication dans un congrès hal-03287829 v1
Image document

BYOL works even without batch statistics

Pierre H. Richemond , Jean-Bastien Grill , Florent Altché , Corentin Tallec , Florian Strub et al.
NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice, Jan 2020, Online, United States
Communication dans un congrès hal-05413292 v1
Image document

Improved sleeping bandits with stochastic action sets and adversarial rewards

Aadirupa Saha , Pierre Gaillard , Michal Valko
ICML 2020 - International Conference on Machine Learning, Jul 2020, Vienna, Austria
Communication dans un congrès hal-02950106 v1
Image document

Active multiple matrix completion with adaptive confidence sets

Andrea Locatelli , Alexandra Carpentier , Michal Valko
International Conference on Artificial Intelligence and Statistics, 2019, Okinawa, Japan
Communication dans un congrès hal-02387468 v1
Image document

Gaussian process optimization with adaptive sketching: Scalable and no regret

Daniele Calandriello , Luigi Carratino , Alessandro Lazaric , Michal Valko , Lorenzo Rosasco
Conference on Learning Theory, 2019, Phoenix, United States
Communication dans un congrès hal-02144311 v1
Image document

Exact sampling of determinantal point processes with sublinear time preprocessing

Michał Dereziński , Daniele Calandriello , Michal Valko
Neural Information Processing Systems, 2019, Vancouver, Canada
Communication dans un congrès hal-02387524 v1
Image document

Exploiting structure of uncertainty for efficient matroid semi-bandits

Pierre Perrault , Vianney Perchet , Michal Valko
International Conference on Machine Learning, 2019, Long Beach, United States
Communication dans un congrès hal-02387478 v1
Image document

Finding the bandit in a graph: Sequential search-and-stop

Pierre Perrault , Vianney Perchet , Michal Valko
22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Apr 2019, Okinawa, Japan
Communication dans un congrès hal-02387465 v1
Image document

A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption

Peter Bartlett , Victor Gabillon , Michal Valko
Algorithmic Learning Theory, 2019, Chicago, United States
Communication dans un congrès hal-01885368 v2
Image document

On two ways to use determinantal point processes for Monte Carlo integration -- Long version

Guillaume Gautier , Rémi Bardenet , Michal Valko
NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Jun 2019, Vancouver, Canada
Communication dans un congrès hal-02277739 v1
Image document

A simple dynamic bandit algorithm for hyper-parameter tuning

Xuedong Shang , Emilie Kaufmann , Michal Valko
Workshop on Automated Machine Learning at International Conference on Machine Learning, AutoML@ICML 2019 - 6th ICML Workshop on Automated Machine Learning, Jun 2019, Long Beach, United States
Communication dans un congrès hal-02145200 v1
Image document

Rotting bandits are not harder than stochastic ones

Julien Seznec , Andrea Locatelli , Alexandra Carpentier , Alessandro Lazaric , Michal Valko
International Conference on Artificial Intelligence and Statistics, 2019, Naha, Japan
Communication dans un congrès hal-01936894 v2
Image document

General parallel optimization without a metric

Xuedong Shang , Emilie Kaufmann , Michal Valko
Algorithmic Learning Theory, 2019, Chicago, United States
Communication dans un congrès hal-02047225 v2

Optimizing human learning workshop eliciting adaptive sequences for learning (WeASeL)

Popineau, Fabrice , Valko, Michal , Vie, Jill-Jênn
Machine Learning Conference, Jan 2019, Online, United States
Communication dans un congrès hal-05437169 v1
Image document

Les processus ponctuels déterminantaux en apprentissage automatique

Guillaume Gautier , Rémi Bardenet , Michal Valko
GRETSI 2019 - XXVIIe Colloque sur le Traitement du Signal et des Images, Jan 2019, Online, France
Communication dans un congrès hal-05413294 v1
Image document

Multiagent evaluation under incomplete information

Mark Rowland , Shayegan Omidshafiei , Karl Tuyls , Julien Pérolat , Michal Valko et al.
NeurIPS 2020 - 33rd Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada
Communication dans un congrès hal-05413293 v1
Image document

Planning in entropy-regularized Markov decision processes and games

Jean-Bastien Grill , Omar D Domingues , Pierre Ménard , Rémi Munos , Michal Valko
Neural Information Processing Systems, 2019, Vancouver, Canada
Communication dans un congrès hal-02387515 v1
Image document

Scale-free adaptive planning for deterministic dynamics & discounted rewards

Peter Bartlett , Victor Gabillon , Jennifer Healey , Michal Valko
International Conference on Machine Learning, 2019, Long Beach, United States
Communication dans un congrès hal-02387484 v1
Image document

Optimistic optimization of a Brownian

Jean-Bastien Grill , Michal Valko , Rémi Munos
NeurIPS 2018 - Thirty-second Conference on Neural Information Processing Systems, Dec 2018, Montréal, Canada
Communication dans un congrès hal-01906601 v2
Image document

Adaptive black-box optimization got easier: HCT only needs local smoothness

Xuedong Shang , Emilie Kaufmann , Michal Valko
European Workshop on Reinforcement Learning, Oct 2018, Lille, France
Communication dans un congrès hal-01874637 v1
Image document

Improved large-scale graph learning through ridge spectral sparsification

Daniele Calandriello , Ioannis Koutis , Alessandro Lazaric , Michal Valko
International Conference on Machine Learning, Jul 2018, Stockholm, Sweden
Communication dans un congrès hal-01810980 v1
Image document

Best of both worlds: Stochastic & adversarial best-arm identification

Yasin Abbasi-Yadkori , Peter Bartlett , Victor Gabillon , Alan Malek , Michal Valko
Conference on Learning Theory, 2018, Stockholm, Sweden
Communication dans un congrès hal-01808948 v6
Image document

Compressing the Input for CNNs with the First-Order Scattering Transform

Edouard Oyallon , Eugene Belilovsky , Sergey Zagoruyko , Michal Valko
ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany
Communication dans un congrès hal-01850921 v1
Image document

Second-Order Kernel Online Convex Optimization with Adaptive Sketching

Daniele Calandriello , Alessandro Lazaric , Michal Valko
International Conference on Machine Learning, 2017, Sydney, Australia
Communication dans un congrès hal-01537799 v1
Image document

Online influence maximization under independent cascade model with semi-bandit feedback

Zheng Wen , Branislav Kveton , Michal Valko , Sharan Vaswani
Neural Information Processing Systems, Dec 2017, Long Beach, United States. pp.1-24
Communication dans un congrès hal-01643976 v1
Image document

Efficient second-order online kernel learning with adaptive embedding

Daniele Calandriello , Alessandro Lazaric , Michal Valko
Neural Information Processing Systems, 2017, Long Beach, United States
Communication dans un congrès hal-01643961 v1
Image document

Zonotope hit-and-run for efficient sampling from projection DPPs

Guillaume Gautier , Rémi Bardenet , Michal Valko
International Conference on Machine Learning, 2017, Sydney, Australia
Communication dans un congrès hal-01526577 v2
Image document

Distributed adaptive sampling for kernel matrix approximation

Daniele Calandriello , Alessandro Lazaric , Michal Valko
International Conference on Artificial Intelligence and Statistics, 2017, Fort Lauderdale, United States
Communication dans un congrès hal-01482760 v1
Image document

Trading off rewards and errors in multi-armed bandits

Akram Erraqabi , Alessandro Lazaric , Michal Valko , Emma Brunskill , Yun-En Liu
International Conference on Artificial Intelligence and Statistics, 2017, Fort Lauderdale, United States
Communication dans un congrès hal-01482765 v1
Image document

Online learning with noisy side observations

Tomáš Kocák , Gergely Neu , Michal Valko
International Conference on Artificial Intelligence and Statistics, May 2016, Seville, Spain
Communication dans un congrès hal-01303377 v1
Image document

Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning

Jean-Bastien Grill , Michal Valko , Rémi Munos
Neural Information Processing Systems, Dec 2016, Barcelona, Spain
Communication dans un congrès hal-01389107 v3
Image document

Pliable rejection sampling

Akram Erraqabi , Michal Valko , Alexandra Carpentier , Odalric-Ambrym Maillard
International Conference on Machine Learning, Jun 2016, New York City, United States
Communication dans un congrès hal-01322168 v1
Image document

Analysis of Nyström method with sequential ridge leverage score sampling

Daniele Calandriello , Alessandro Lazaric , Michal Valko
Uncertainty in Artificial Intelligence, Jun 2016, New York City, United States
Communication dans un congrès hal-01343674 v1
Image document

Rewards and errors in multi-arm bandits for interactive education

Akram Erraqabi , Alessandro Lazaric , Michal Valko , Emma Brunskill , Yun-En Liu
Challenges in Machine Learning: Gaming and Education workshop at Neural Information Processing Systems, 2016, Barcelona, Spain
Communication dans un congrès hal-01482764 v1
Image document

Revealing graph bandits for maximizing local influence

Alexandra Carpentier , Michal Valko
International Conference on Artificial Intelligence and Statistics, May 2016, Seville, Spain
Communication dans un congrès hal-01304020 v3
Image document

Pack only the essentials: Adaptive dictionary learning for kernel ridge regression

Daniele Calandriello , Alessandro Lazaric , Michal Valko
Adaptive and Scalable Nonparametric Methods in Machine Learning at Neural Information Processing Systems, 2016, Barcelona, Spain
Communication dans un congrès hal-01482756 v1
Image document

Online learning with Erdős-Rényi side-observation graphs

Tomáš Kocák , Gergely Neu , Michal Valko
Uncertainty in Artificial Intelligence, Jun 2016, New York City, United States
Communication dans un congrès hal-01320588 v1
Image document

Cheap Bandits

Manjesh Kumar Hanawal Hanawal , Venkatesh Saligrama , Michal Valko , Rémi Munos
International Conference on Machine Learning, 2015, Lille, France
Communication dans un congrès hal-01153540 v1
Image document

Large-scale semi-supervised learning with online spectral graph sparsification

Daniele Calandriello , Alessandro Lazaric , Michal Valko
Resource-Efficient Machine Learning workshop at International Conference on Machine Learning, Jul 2015, Lille, France
Communication dans un congrès hal-01544929 v1
Image document

Black-box optimization of noisy functions with unknown smoothness

Jean-Bastien Grill , Michal Valko , Rémi Munos
Neural Information Processing Systems, 2015, Montréal, Canada
Communication dans un congrès hal-01222915 v4
Image document

Maximum Entropy Semi-Supervised Inverse Reinforcement Learning

Julien Audiffren , Michal Valko , Alessandro Lazaric , Mohammad Ghavamzadeh
International Joint Conference on Artificial Intelligence, Jul 2015, Bueons Aires, Argentina
Communication dans un congrès hal-01146187 v1
Image document

Simple regret for infinitely many armed bandits

Alexandra Carpentier , Michal Valko
International Conference on Machine Learning, Jul 2015, Lille, France
Communication dans un congrès hal-01153538 v1
Image document

Bandits attack function optimization

Philippe Preux , Rémi Munos , Michal Valko
IEEE Congress on Evolutionary Computation, Jul 2014, Beijing, China
Communication dans un congrès hal-00978637 v1
Image document

Online combinatorial optimization with stochastic decision sets and adversarial losses

Gergely Neu , Michal Valko
Neural Information Processing Systems, Dec 2014, Montréal, Canada
Communication dans un congrès hal-01079355 v2
Image document

Spectral Thompson Sampling

Tomáš Kocák , Michal Valko , Rémi Munos , Shipra Agrawal
AAAI Conference on Artificial Intelligence, Jul 2014, Québec City, Canada
Communication dans un congrès hal-00981575 v2
Image document

MESSI: Maximum Entropy Semi-Supervised Inverse Reinforcement Learning

Julien Audiffren , Michal Valko , Alessandro Lazaric , Mohammad Ghavamzadeh
NIPS Workshop on Novel Trends and Applications in Reinforcement Learning, 2014, Montreal, Canada
Communication dans un congrès hal-01177446 v1
Image document

Efficient learning by implicit exploration in bandit problems with side observations

Tomáš Kocák , Gergely Neu , Michal Valko , Rémi Munos
Neural Information Processing Systems, Dec 2014, Montréal, Canada
Communication dans un congrès hal-01079351 v2
Image document

Spectral Bandits for Smooth Graph Functions with Applications in Recommender Systems

Tomáš Kocák , Michal Valko , Rémi Munos , Branislav Kveton , Shipra Agrawal
AAAI Workshop on Sequential Decision-Making with Big Data, Jul 2014, Québec City, Canada
Communication dans un congrès hal-01045036 v1
Image document

Extreme bandits

Alexandra Carpentier , Michal Valko
Neural Information Processing Systems, Dec 2014, Montréal, Canada
Communication dans un congrès hal-01079354 v2
Image document

Spectral Bandits for Smooth Graph Functions

Michal Valko , Rémi Munos , Branislav Kveton , Tomáš Kocák
International Conference on Machine Learning, May 2014, Beijing, China
Communication dans un congrès hal-00986818 v3
Image document

Learning from a Single Labeled Face and a Stream of Unlabeled Data

Branislav Kveton , Michal Valko
10th IEEE International Conference on Automatic Face and Gesture Recognition, Apr 2013, Shanghai, China
Communication dans un congrès hal-00749197 v2
Image document

Finite-Time Analysis of Kernelised Contextual Bandits

Michal Valko , Nathan Korda , Rémi Munos , Ilias Flaounas , Nello Cristianini
Uncertainty in Artificial Intelligence, Jul 2013, Bellevue, United States
Communication dans un congrès hal-00826946 v1
Image document

Stochastic Simultaneous Optimistic Optimization

Michal Valko , Alexandra Carpentier , Rémi Munos
International Conference on Machine Learning, Jun 2013, Atlanta, United States
Communication dans un congrès hal-00789606 v2
Image document

Semi-Supervised Apprenticeship Learning

Michal Valko , Mohammad Ghavamzadeh , Alessandro Lazaric
The 10th European Workshop on Reinforcement Learning (EWRL 2012), Jun 2012, Edinburgh, United Kingdom. pp.131-141
Communication dans un congrès hal-00747921 v2
Image document

Conditional Anomaly Detection Using Soft Harmonic Functions: An Application to Clinical Alerting

Michal Valko , Hamed Valizadegan , Branislav Kveton , Gregory Cooper , Milos Hauskrecht
The 28th International Conference on Machine Learning Workshop on Machine Learning for Global Challenges, Jun 2011, Seattle, United States
Communication dans un congrès hal-00642313 v1
Image document

Conditional Anomaly Detection with Soft Harmonic Functions

Michal Valko , Branislav Kveton , Hamed Valizadegan , Gregory Cooper , Milos Hauskrecht
Proceedings of the 2011 IEEE International Conference on Data Mining, Dec 2011, Vancouver, Canada
Communication dans un congrès hal-00641081 v1
Image document

Feature importance analysis for patient management decisions

Michal Valko , Milos Hauskrecht
13th International Congress on Medical Informatics MEDINFO 2010, Sep 2010, Cape Town, South Africa. pp.861-865, ⟨10.3233/978-1-60750-588-4-861⟩
Communication dans un congrès hal-00643123 v1
Image document

Semi-Supervised Learning with Max-Margin Graph Cuts

Branislav Kveton , Michal Valko , Ali Rahimi , Ling Huang
International Conference on Artificial Intelligence and Statistics, May 2010, Chia Laguna, Sardinia, Italy
Communication dans un congrès hal-00642891 v1
Image document

Online Semi-Supervised Learning on Quantized Graphs

Michal Valko , Branislav Kveton , Huang Ling , Ting Daniel
Uncertainty in Artificial Intelligence, Jun 2010, Catalina Island, United States
Communication dans un congrès hal-00642361 v1
Image document

Online Semi-Supervised Perception: Real-Time Learning without Explicit Feedback

Branislav Kveton , Michal Valko , Mathai Phillipose , Ling Huang
4th IEEE Online Learning for Computer Vision Workshop, Jun 2010, San Francisco, United States. ⟨10.1109/CVPRW.2010.5543877⟩
Communication dans un congrès hal-00642999 v1
Image document

Learning predictive models for combinations of heterogeneous proteomic data sources

Michal Valko , Richard Pelikan , Milos Hauskrecht
AMIA Summit on Translational Bioinformatics, Mar 2008, San Francisco, United States
Communication dans un congrès hal-00643349 v1
Image document

Conditional anomaly detection methods for patient-management alert systems

Michal Valko , Gregory F. Cooper , Amy Seybert , Shyam Visweswaran , Melissa Saul et al.
Workshop on Machine Learning in Health Care Applications in The 25th International Conference on Machine Learning, Jul 2008, Helsinki, Finland
Communication dans un congrès hal-00643221 v1
Image document

Distance Metric Learning for Conditional Anomaly Detection

Michal Valko , Milos Hauskrecht
Twenty-First International Florida Artificial Intelligence Research Society Conference, May 2008, Coconut Grove, Florida, United States
Communication dans un congrès hal-00643244 v1
Image document

Evidence-based Anomaly Detection in Clinical Domains

Milos Hauskrecht , Michal Valko , Branislav Kveton , Shyam Visweswaran , Gregory F. Cooper
Annual American Medical Informatics Association Symposium, 2007, Chicago, United States. pp.319--324
Communication dans un congrès hal-00643401 v1
Image document

A Comparison of Chief Complaints and Emergency Department Reports for Identifying Patients with Acute Lower Respiratory Syndrome

Wendy Chapman , John Dowling , Gregory F Cooper , Milos Hauskrecht , Michal Valko
International Society for Disease Surveillance, Oct 2006, Baltimore, United States
Communication dans un congrès hal-00643495 v1
Image document

Evolutionary Feature Selection for Spiking Neural Network Pattern Classifiers

Michal Valko , Nuno Cavalheiro , Marco Castelani
Proceedings of 2005 Portuguese Conference on Artificial Intelligence, Dec 2005, Covilha, Portugal. pp.181-187, ⟨10.1109/EPIA.2005.341291⟩
Communication dans un congrès hal-00643498 v1
Image document

On the approximation relationship between optimizing ratio of submodular (RS) and difference of submodular (DS) functions

Pierre Perrault , Jennifer Healey , Zheng Wen , Michal Valko
2025
Pré-publication, Document de travail hal-05414208 v1
Image document

Understanding the performance gap between online and offline alignment algorithms

Yunhao Tang , Daniel Zhaohan Guo , Zeyu Zheng , Daniele Calandriello , Yuan Cao et al.
2025
Pré-publication, Document de travail hal-05414204 v1
Image document

KL-entropy-regularized RL with a generative model is minimax optimal

Tadashi Kozuno , Wenhao Yang , Nino Vieillard , Toshinori Kitamura , Yunhao Tang et al.
2025
Pré-publication, Document de travail hal-05414206 v1

Accelerating Nash Learning from Human Feedback via Mirror Prox

Daniil Tiapkin , Daniele Calandriello , Denis Belomestny , Eric Moulines , Alexey Naumov et al.
2025
Pré-publication, Document de travail (preprint/prepublication) hal-05155196 v1
Image document

Geometric entropic exploration

Zhaohan Daniel Guo , Mohammad Gheshlaghi Azar , Alaa Saade , Shantanu Thakoor , Bilal Piot et al.
2025
Pré-publication, Document de travail hal-05414207 v1
Image document

Learning to Act Greedily: Polymatroid Semi-Bandits

Branislav Kveton , Zheng Wen , Azin Ashkan , Michal Valko
2026
Pré-publication, Document de travail hal-05414209 v1
Image document

A new bound on the cumulant generating function of Dirichlet processes

Pierre Perrault , Denis Belomestny , Pierre Ménard , Éric Moulines , Alexey Naumov et al.
2025
Pré-publication, Document de travail hal-05414203 v1
Image document

Preference optimization with multi-sample comparisons

Chaoqi Wang , Zhuokai Zhao , Chen Zhu , Karthik Abinav Sankararaman , Michal Valko et al.
2025
Pré-publication, Document de travail hal-05414201 v1
Image document

Sharp deviations bounds for Dirichlet weighted sums with application to analysis of Bayesian algorithms

Denis Belomestny , Pierre Ménard , Alexey Naumov , Daniil Tiapkin , Michal Valko
2025
Pré-publication, Document de travail hal-05414205 v1

Optimal design for reward modeling in RLHF

Antoine Scheid , Étienne Boursier , Alain Durmus , Michael I Jordan , Pierre Ménard et al.
2025
Pré-publication, Document de travail hal-05414202 v1
Image document

RL-finetuning LLMs from on- and off-policy data with a single algorithm

Yunhao Tang , Taco Cohen , David W. Zhang , Michal Valko , Rémi Munos
2026
Pré-publication, Document de travail hal-05414200 v1
Image document

The Llama 3 herd of models

Aaron Grattafiori , Abhimanyu Dubey , Abhinav Jauhri , Abhinav Pandey , Abhishek Kadian et al.
2025
Pré-publication, Document de travail hal-05414211 v1
Image document

Game plan: What AI can do for football, and what football can do for AI

Karl Tuyls , Shayegan Omidshafiei , Paul Muller , Zhe Wang , Jerome Connor et al.
Journal of Artificial Intelligence Research, 2021, 71, pp.41-88. ⟨10.1613/jair.1.12505⟩
Article dans une revue hal-05413287 v1
Image document

Fast sampling from beta-ensembles

Guillaume Gautier , Rémi Bardenet , Michal Valko
Statistics and Computing, 2021, 31 (7), ⟨10.1007/s11222-020-09984-0⟩
Article dans une revue hal-02697647 v1
Image document

Spectral bandits

Tomáš Kocák , Rémi Munos , Branislav Kveton , Shipra Agrawal , Michal Valko
Journal of Machine Learning Research, 2020
Article dans une revue hal-03084249 v1
Image document

DPPy: Sampling Determinantal Point Processes with Python

Guillaume Gautier , Rémi Bardenet , Michal Valko
Journal of Machine Learning Research, 2019
Article dans une revue hal-01879424 v1
Image document

Bayesian Policy Gradient and Actor-Critic Algorithms

Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko
Journal of Machine Learning Research, 2016, 17 (66), pp.1-53
Article dans une revue hal-00776608 v2

Outlier detection for patient monitoring and alerting

Milos Hauskrecht , Iyad Batal , Michal Valko , Shyam Visweswaran , Gregory F Cooper et al.
Journal of Biomedical Informatics, 2013, 46, pp.47-55. ⟨10.1016/j.jbi.2012.08.004⟩
Article dans une revue hal-00742097 v1
Image document

Identification of microbial and proteomic biomarkers in early childhood caries

Thomas C. Hart , Patricia M. Corby , Milos Hauskrecht , Ok Hee Ryu , Richard Pelikan et al.
International Journal of Dentistry, 2011, 2011, pp.196721. ⟨10.1155/2011/196721⟩
Article dans une revue hal-00642074 v1
Image document

Conditional Outlier Detection for Clinical Alerting

Milos Hauskrecht , Michal Valko , Iyad Batal , Gilles Clermont , Shyam Visweswaran et al.
AMIA .. Annual Symposium proceedings [electronic resource] / AMIA Symposium. AMIA Symposium., 2010, 2010, pp.286-90
Article dans une revue hal-00642993 v1
Image document

Bandits on graphs and structures

Michal Valko
Machine Learning [stat.ML]. École normale supérieure de Cachan - ENS Cachan, 2016
HDR tel-01359757 v1
Image document

Feature Selection and Dimensionality Reduction in Genomics and Proteomics

Milos Hauskrecht , Richard Pelikan , Michal Valko , James Lyons-Weiler
Werner Dubitzky, Martin Granzow and Daniel Berrar. Fundamentals of Data Mining in Genomics and Proteomics, Springer, pp.149-172, 2006, ⟨10.1007/978-0-387-47509-7⟩
Chapitre d'ouvrage hal-00643496 v1