Maxim Kodryan
6 papers · 2019–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🗺️
Taxonomy Completionist
(16)
🔥
Unstoppable · Bronze
❓
The Questioner
Venues
Top co-authors
Research topics
Keywords
neural network
(3)
batch normalization
(2)
model compression
(2)
neural network training
(1)
variational inference
(1)
bayesian inference
(1)
neural network optimization
(1)
loss landscape
(1)
tensor decomposition
(1)
automatic relevance determination
(1)
learning rate
(1)
recurrent neural network
(1)
language model
(1)
weight decay
(1)
uncertainty estimation
(1)
weight averaging
(1)
local geometry
(1)
sparse feature
(1)
weight pruning
(1)
flat minima
(1)
Papers
Where Do Large Learning Rates Lead Us?
NeurIPS 2024
MARS: Masked Automatic Ranks Selection in Tensor Decompositions
AISTATS 2023
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes
NeurIPS 2022
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay
NeurIPS 2021
On Power Laws in Deep Ensembles
NeurIPS 2020
Efficient Language Modeling with Automatic Relevance Determination in Recurrent Neural Networks
ACL 2019