Margalit Glasgow
7 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(3)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ICLR (3)
COLT (2)
NIPS (2)
Top co-authors
Keywords
stochastic optimization
(1)
representation learning
(1)
learning theory
(1)
contrastive learning
(1)
data augmentation
(1)
distributed learning
(1)
gradient descent
(1)
communication efficiency
(1)
data heterogeneity
(1)
foundation model
(1)
mean-field analysis
(1)
local sgd
(1)
kernel methods
(1)
neural network
(1)
mini-batch gradient descent
(1)
viewmaker network
(1)
label-destroying augmentation
(1)
Papers
Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon
COLT 2025
Convergence of Distributed Adaptive Optimization with Local Updates
ICLR 2025
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication
COLT 2024
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
ICLR 2024
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
NIPS 2023
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
ICLR 2023
Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning
NIPS 2023