Anastasia Volkova
Publications
Publications
|
|
Quantization-aware training: a tradeoff between training and fine-tuning for domain-specific language modelsAccML 2026 - 8th Workshop on Accelerated Machine Learning, Jan 2026, Krakow (Cracovie), Poland |
|
|
Reducing the Hardware Gap for Custom Accelerators through Quantization Aware TrainingAccML 2026 - 8th Workshop on Accelerated Machine Learning, Jan 2026, Krakow (Cracovie), Poland |
|
|
Training for Mixed-Precision Integer Weights, Activations and Embeddings in BERTDASIP 2026: Workshop on Design and Architectures for Signal and Image Processing, Jan 2026, Krakow (Cracovie), Poland |
|
|
Towards optimal reconfigurable constant multipliers28th Conference on Digital System Design (DSD), Euromicro, Sep 2025, Salerno, Italy. pp.418-425, ⟨10.1109/DSD67783.2025.00064⟩ |
|
|
A new Constraint Programming model for the Multiple Constant MultiplicationModRef 2025 - 24th workshop on Constraint Modelling and Reformulation, Aug 2025, Glasgow, United Kingdom |
|
|
Hardware-optimal digital FIR filters: one ILP to rule them all and in faithfulness bind them2023 Asilomar Conference on Signals, Systems, and Computers, Oct 2023, Asilomar, United States |
|
|
Towards Fixed-Point Formats Determination for Faust ProgramsJournées d'Informatique Musicale 2024, May 2024, Marseille, France |
|
|
Multiple Constant Multiplication: From Target Constants to Optimized Pipelined Adder Graphs2023 33rd International Conference on Field-Programmable Logic and Applications (FPL), Sep 2023, Gothenburg, France. pp.137-143, ⟨10.1109/FPL60245.2023.00027⟩ |
|
|
Hardware-Aware Quantization for Multiplierless Neural Network ControllersThe IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), Nov 2022, Shenzhen, China. ⟨10.1109/APCCAS55924.2022.10090271⟩ |
|
|
A New Model for the Multiple Constant Multiplication Problem23ème congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision, INSA Lyon, Feb 2022, Villeurbanne - Lyon, France |
|
|
Truncated Multiple Constant Multiplication with Minimal Number of Full AddersISCAS 2022, May 2022, Austin, Texas, United States. pp.263-267, ⟨10.1109/ISCAS48785.2022.9937441⟩ |
|
|
Towards Arithmetic-Centered Filter DesignARITH 2021 - 28th IEEE Symposium on Computer Arithmetic, Jun 2021, Torino, Italy. pp.1-4, ⟨10.1109/ARITH51176.2021.00032⟩ |
|
|
A Framework for Semi-Automatic Precision and Accuracy Analysis for Fast and Rigorous Deep LearningIEEE Symposium on Computer Arithmetic (ARITH), Jun 2020, Portland, United States. ⟨10.1109/arith48897.2020.00023⟩ |
|
|
Semi-automatic implementation of the complementary error functionARITH 2019 - 26th IEEE Symposium on Computer Arithmetic, Jun 2019, Kyoto, Japan. pp.1-8 |
|
|
FiXiF toolbox : validated numerics for sound digital filter implementations18th International Symposium on Scientific Computing, Computer Arithmetics and Verified Numerics., Sep 2018, Tokyo, Japan |
|
|
Error analysis methods for the fixed-point implementation of linear systems2017 IEEE International Workshop on Signal Processing Systems (SiPS), Oct 2017, Lorient, France. ⟨10.1109/SiPS.2017.8109991⟩ |
|
|
Reliable verification of digital implemented filters against frequency specifications24th IEEE Symposium on Computer Arithmetic (ARITH 24), Jul 2017, London, United Kingdom |
|
|
Multiplierless Unified Architecture for Mixed Radix−2/3/4 FFTs25th European Signal Processing Conference, EUSIPCO 2017,, Aug 2017, Kos island, Greece |
|
|
Computing the Worst-Case Peak Gain of Digital Filter in Interval Arithmetic17th International Symposium on Scientific Computing, Computer Arithmetics and Verified Numerics. , Sep 2016, Uppsala, Sweden |
|
|
Reliable fixed-point implementation of linear data-flowsIEEE International Workshop on Signal Processing Systems (SiPS), Oct 2016, Dallas, United States |
|
|
Reliable evaluation of the Worst-Case Peak Gain matrix in multiple precisionARITH 22 - 22nd IEEE Symposium on Computer Arithmetic, Jun 2015, Lyon, France. pp.96-103, ⟨10.1109/ARITH.2015.14⟩ |
|
|
Determining fixed-point formats for a digital filter implementation using the worst-case peak gain measure49th Asilomar Conference on Signals, Systems and Computers , Nov 2015, Pacific Grove, CA United States. pp.737-741, ⟨10.1109/ACSSC.2015.7421231⟩ |
|
|
FIXED-POINT IMPLEMENTATION OF LATTICE WAVE DIGITAL FILTER: COMPARISON AND ERROR ANALYSIS23rd European Signal Processing Conference, EUSIPCO 2015, Aug 2015, Nice, France |
|
|
Reconfigurable Constant Multipliers: Hardware Models, Optimization Algorithm and Applications2026 |
|
|
Contribution to Error Analysis of Deep Neural Networks: Case of the Activation Functions2025 |
|
|
KANHard: Training Hardware-Friendly Kolmogorov-Arnold Networks2025 |
|
|
Entre performance et frugalité en TAL : Approches pour la réduction de la taille des (L)LMs2024 |
|
|
A New Model for the Multiple Constant Multiplication Problem2021 |
|
|
Multiplierless Processing Element for Non-Power-of-Two FFTs2018 |
|
|
Design of optimal multiplierless digital filtersUniversité de Nantes. 2020 |
|
|
Towards reliable implementation of digital filtersComputer Arithmetic. Université Pierre et Marie Curie - Paris VI, 2017. English. ⟨NNT : 2017PA066579⟩ |