Maxim Kodryan

According to our database, Maxim Kodryan authored at least 6 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Large Learning Rates Improve Generalization: But How Large Are We Talking About?

Ekaterina Lobacheva, Eduard Pockonechnyy, Maxim Kodryan, Dmitry P. Vetrov

CoRR, 2023

MARS: Masked Automatic Ranks Selection in Tensor Decompositions.

Maxim Kodryan, Dmitry Kropotov, Dmitry P. Vetrov

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes.

Maxim Kodryan, Ekaterina Lobacheva, Maksim Nakhodnov, Dmitry P. Vetrov

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay.

Ekaterina Lobacheva, Maxim Kodryan, Nadezhda Chirkova, Andrey Malinin, Dmitry P. Vetrov

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

On Power Laws in Deep Ensembles.

Ekaterina Lobacheva, Nadezhda Chirkova, Maxim Kodryan, Dmitry P. Vetrov

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Efficient Language Modeling with Automatic Relevance Determination in Recurrent Neural Networks.

Maxim Kodryan, Artem M. Grachev, Dmitry I. Ignatov, Dmitry P. Vetrov

Proceedings of the 4th Workshop on Representation Learning for NLP, 2019