Julia Gusak

Publication Activity (10 Years)

Years Active: 2016-2023
Publications (10 Years): 22

Top Topics

Sensitivity Analysis

Tensor Decomposition

Quantization Noise

Top Venues

SIAM J. Math. Data Sci.

Publications

Viktoria Chekalina, Georgii S. Novikov, Julia Gusak, Ivan V. Oseledets, Alexander Panchenko
Efficient GPT Model Pre-training using Tensor Train Matrix Representation. CoRR (2023)
Daria Cherniuk, Stanislav Abukhovich, Anh Huy Phan, Ivan V. Oseledets, Andrzej Cichocki, Julia Gusak
Quantization Aware Factorization for Deep Neural Network Compression. CoRR (2023)
Xunyi Zhao, Théotime Le Hellard, Lionel Eyraud-Dubois, Julia Gusak, Olivier Beaumont
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch. ICML (2023)
Georgii Sergeevich Novikov, Daniel Bershatsky, Julia Gusak, Alex Shonenkov, Denis Valerievich Dimitrov, Ivan V. Oseledets
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction. ICML (2023)
Viktoria Chekalina, Georgiy Novikov, Julia Gusak, Alexander Panchenko, Ivan V. Oseledets
Efficient GPT Model Pre-training using Tensor Train Matrix Representation. PACLIC (2023)
Xunyi Zhao, Théotime Le Hellard, Lionel Eyraud, Julia Gusak, Olivier Beaumont
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch. CoRR (2023)
Daniel Bershatsky, Aleksandr Mikhalev, Alexandr Katrutsa, Julia Gusak, Daniil Merkulov, Ivan V. Oseledets
Memory-Efficient Backpropagation through Large Linear Layers. CoRR (2022)
Julia Gusak, Daria Cherniuk, Alena Shilova, Alexandr Katrutsa, Daniel Bershatsky, Xunyi Zhao, Lionel Eyraud-Dubois, Oleh Shliazhko, Denis Dimitrov, Ivan V. Oseledets, Olivier Beaumont
Survey on Efficient Training of Large Neural Networks. IJCAI (2022)
Julia Gusak, Daria Cherniuk, Alena Shilova, Alexandr Katrutsa, Daniel Bershatsky, Xunyi Zhao, Lionel Eyraud-Dubois, Oleg Shlyazhko, Denis Dimitrov, Ivan V. Oseledets, Olivier Beaumont
Survey on Large Scale Neural Network Training. CoRR (2022)
Georgii S. Novikov, Daniel Bershatsky, Julia Gusak, Alex Shonenkov, Denis Dimitrov, Ivan V. Oseledets
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction. CoRR (2022)
Julia Gusak, Alexandr Katrutsa, Talgat Daulbaev, Andrzej Cichocki, Ivan V. Oseledets
Meta-Solver for Neural Ordinary Differential Equations. CoRR (2021)
Talgat Daulbaev, Alexandr Katrutsa, Larisa Markeeva, Julia Gusak, Andrzej Cichocki, Ivan V. Oseledets
Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs. NeurIPS (2020)
Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev, Julia Gusak, Ivan V. Oseledets, Zheng Zhang
Active Subspace of Neural Networks: Structural Analysis and Universal Attacks. SIAM J. Math. Data Sci. 2 (4) (2020)
Anh Huy Phan, Konstantin Sobolev, Konstantin Sozykin, Dmitry Ermilov, Julia Gusak, Petr Tichavský, Valeriy Glukhov, Ivan V. Oseledets, Andrzej Cichocki
Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network. CoRR (2020)
Anh Huy Phan, Konstantin Sobolev, Konstantin Sozykin, Dmitry Ermilov, Julia Gusak, Petr Tichavský, Valeriy Glukhov, Ivan V. Oseledets, Andrzej Cichocki
Stable Low-Rank Tensor Decomposition for Compression of Convolutional Neural Network. ECCV (29) (2020)
Talgat Daulbaev, Alexandr Katrutsa, Larisa Markeeva, Julia Gusak, Andrzej Cichocki, Ivan V. Oseledets
Interpolated Adjoint Method for Neural ODEs. CoRR (2020)
Julia Gusak, Larisa Markeeva, Talgat Daulbaev, Alexandr Katrutsa, Andrzej Cichocki, Ivan V. Oseledets
Towards Understanding Normalization in Neural ODEs. CoRR (2020)
Talgat Daulbaev, Julia Gusak, Evgeny Ponomarev, Andrzej Cichocki, Ivan V. Oseledets
Reduced-Order Modeling of Deep Neural Networks. CoRR (2019)
Julia Gusak, Maksym Kholyavchenko, Evgeny Ponomarev, Larisa Markeeva, Ivan V. Oseledets, Andrzej Cichocki
One time is not enough: iterative tensor decomposition for neural network compression. CoRR (2019)
Chunfeng Cui, Kaiqi Zhang, Talgat Daulbaev, Julia Gusak, Ivan V. Oseledets, Zheng Zhang
Active Subspace of Neural Networks: Structural Analysis and Universal Attacks. CoRR (2019)
Julia Gusak, Maksym Kholyavchenko, Evgeny Ponomarev, Larisa Markeeva, Philip Blagoveschensky, Andrzej Cichocki, Ivan V. Oseledets
Automated Multi-Stage Compression of Neural Networks. ICCV Workshops (2019)
Ekaterina Bulinskaya, Julia Gusak
Optimal Control and Sensitivity Analysis for Two Risk Models. Commun. Stat. Simul. Comput. 45 (5) (2016)