Ekaterina Lobacheva
9 papers · 2015–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (21) π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (5) π Academic Marathon (10)
π
Interdisciplinary Bridge
π
Cross-Pollinator
(13)
π
Renaissance Researcher
(5)
π₯
Unstoppable
(6)
β
The Questioner
Conferences
NIPS (5)
AAAI (1)
ACL (1)
EMNLP (1)
ICCV (1)
Top co-authors
Keywords
neural network
(3)
batch normalization
(2)
image segmentation
(1)
neural network training
(1)
transfer learning
(1)
ensemble learning
(1)
recurrent neural network
(1)
long short-term memory
(1)
language modeling
(1)
neural network optimization
(1)
loss landscape
(1)
structured sparsity
(1)
energy optimization
(1)
learning rate
(1)
gaussian mixture model
(1)
text classification
(1)
feature learning
(1)
language model
(1)
scaling law
(1)
neural network compression
(1)
Papers
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning
ACL 2025
Where Do Large Learning Rates Lead Us?
NIPS 2024
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
NIPS 2023
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes
NIPS 2022
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay
NIPS 2021
On Power Laws in Deep Ensembles
NIPS 2020
Structured Sparsification of Gated Recurrent Neural Networks
AAAI 2020
Bayesian Compression for Natural Language Processing
EMNLP 2018
Joint Optimization of Segmentation and Color Clustering
ICCV 2015