Ekaterina Lobacheva

30 papers A* 8A 1Journal 18Unranked 3
YearRankTypeTitle / Venue / Authors
2025 J jnl
Can Training Dynamics of Scale-Invariant Neural Networks Be Explained by the Thermodynamics of an Ideal Gas?
CoRR
Ildus Sadrtdinov, Ekaterina Lobacheva, Ivan Klimov, Mikhail I. Katsnelson, Dmitry P. Vetrov
2025 J jnl
SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training.
CoRR
Ildus Sadrtdinov, Ivan Klimov, Ekaterina Lobacheva, Dmitry P. Vetrov
2025 — conf
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning.
ACL (1)
Andrei Mircea, Supriyo Chakraborty, Nima Chitsazan, Irina Rish, Ekaterina Lobacheva
2025 J jnl
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning.
CoRR
Andrei Mircea, Supriyo Chakraborty, Nima Chitsazan, Irina Rish, Ekaterina Lobacheva
2024 A* conf
Where Do Large Learning Rates Lead Us?
NeurIPS
Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva, Dmitry P. Vetrov
2024 J jnl
Where Do Large Learning Rates Lead Us?
CoRR
Ildus Sadrtdinov, Maxim Kodryan, Eduard Pokonechny, Ekaterina Lobacheva, Dmitry P. Vetrov
2023 J jnl
Large Learning Rates Improve Generalization: But How Large Are We Talking About?
CoRR
Ekaterina Lobacheva, Eduard Pockonechnyy, Maxim Kodryan, Dmitry P. Vetrov
2023 A* conf
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning.
NeurIPS
Ildus Sadrtdinov, Dmitrii Pozdeev, Dmitry P. Vetrov, Ekaterina Lobacheva
2023 J jnl
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning.
CoRR
Ildus Sadrtdinov, Dmitrii Pozdeev, Dmitry P. Vetrov, Ekaterina Lobacheva
2022 A* conf
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes.
NeurIPS
Maxim Kodryan, Ekaterina Lobacheva, Maksim Nakhodnov, Dmitry P. Vetrov
2022 J jnl
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes.
CoRR
Maxim Kodryan, Ekaterina Lobacheva, Maksim Nakhodnov, Dmitry P. Vetrov
2021 J jnl
Machine Learning Methods for Spectral Efficiency Prediction in Massive MIMO Systems.
CoRR
Evgeny Bobrov, Sergey Troshin, Nadezhda Chirkova, Ekaterina Lobacheva, Sviatoslav Panchenko, Dmitry P. Vetrov, Dmitry Kropotov
2021 J jnl
On the Memorization Properties of Contrastive Learning.
CoRR
Ildus Sadrtdinov, Nadezhda Chirkova, Ekaterina Lobacheva
2021 A* conf
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay.
NeurIPS
Ekaterina Lobacheva, Maxim Kodryan, Nadezhda Chirkova, Andrey Malinin, Dmitry P. Vetrov
2021 J jnl
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay.
CoRR
Ekaterina Lobacheva, Maxim Kodryan, Nadezhda Chirkova, Andrey Malinin, Dmitry P. Vetrov
2020 J jnl
Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?
CoRR
Nadezhda Chirkova, Ekaterina Lobacheva, Dmitry P. Vetrov
2020 A* conf
On Power Laws in Deep Ensembles.
NeurIPS
Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, Dmitry P. Vetrov
2020 J jnl
On Power Laws in Deep Ensembles.
CoRR
Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, Dmitry P. Vetrov
2020 A* conf
Structured Sparsification of Gated Recurrent Neural Networks.
AAAI
Ekaterina Lobacheva, Nadezhda Chirkova, Alexander Markovich, Dmitry P. Vetrov
2019 J jnl
Structured Sparsification of Gated Recurrent Neural Networks.
CoRR
Ekaterina Lobacheva, Nadezhda Chirkova, Alexander Markovich, Dmitry P. Vetrov
2018 A* conf
Bayesian Compression for Natural Language Processing.
EMNLP
Nadezhda Chirkova, Ekaterina Lobacheva, Dmitry P. Vetrov
2018 J jnl
Bayesian Compression for Natural Language Processing.
CoRR
Nadezhda Chirkova, Ekaterina Lobacheva, Dmitry P. Vetrov
2018 J jnl
Bayesian Sparsification of Gated Recurrent Neural Networks.
CoRR
Ekaterina Lobacheva, Nadezhda Chirkova, Dmitry P. Vetrov
2018 — conf
Monotonic models for real-time dynamic malware detection.
ICLR (Workshop)
Alexander Chistyakov, Ekaterina Lobacheva, Alexander Shevelev, Alexey Romanenko
2018 J jnl
Monotonic models for real-time dynamic malware detection.
CoRR
Alexander Chistyakov, Ekaterina Lobacheva, Alexander Shevelev, Alexey Romanenko
2018 J jnl
Semantic embeddings for program behavior patterns.
CoRR
Alexander Chistyakov, Ekaterina Lobacheva, Arseny Kuznetsov, Alexey Romanenko
2017 J jnl
Bayesian Sparsification of Recurrent Neural Networks.
CoRR
Ekaterina Lobacheva, Nadezhda Chirkova, Dmitry P. Vetrov
2017 — conf
Semantic embeddings for program behaviour patterns.
ICLR (Workshop)
Alexander Chistyakov, Ekaterina Lobacheva, Arseny Kuznetsov, Alexey Romanenko
2016 A conf
Deep Part-Based Generative Shape Model with Latent Variables.
BMVC
Alexander Kirillov, Mikhail Gavrikov, Ekaterina Lobacheva, Anton Osokin, Dmitry P. Vetrov
2015 A* conf
Joint Optimization of Segmentation and Color Clustering.
ICCV
Ekaterina Lobacheva, Olga Veksler, Yuri Boykov