Margalit Glasgow
7 papers · 2023–2025 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory · Machine Learning
(6)
Deep Learning
(3)
Mathematics & Optimization
(2)
Optimization
(2)
Application Areas
(1)
Architectures
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
representation learning
(1)
learning theory
(1)
contrastive learning
(1)
stochastic gradient descent
(1)
feature learning
(1)
convex optimization
(1)
data augmentation
(1)
sample complexity
(1)
communication complexity
(1)
distributed learning
(1)
neural network optimization
(1)
uniform convergence
(1)
gradient descent
(1)
signal-to-noise ratio
(1)
communication efficiency
(1)
projected gradient descent
(1)
generalization bound
(1)
adaptive optimization
(1)
data heterogeneity
(1)
stochastic optimization
(1)
Papers
Convergence of Distributed Adaptive Optimization with Local Updates
ICLR 2025
Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon
COLT 2025
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
ICLR 2024
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication
COLT 2024
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
NeurIPS 2023
Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning
NeurIPS 2023
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence
ICLR 2023