Margalit Glasgow

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 16

Top Topics

Distributed Heterogeneous

Generalization Bounds

Sample Complexity

Top Venues

IEEE J. Sel. Areas Inf. Theory

Publications

Margalit Glasgow
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem. ICLR (2024)
Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication. COLT (2024)
Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication. CoRR (2024)
Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. ICLR (2023)
Arvind Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. NeurIPS (2023)
Alex Tamkin, Margalit Glasgow, Xiluo He, Noah D. Goodman
Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning. NeurIPS (2023)
Margalit Glasgow, Alexander Rakhlin
Lower Bounds for γ-Regret via the Decision-Estimation Coefficient. CoRR (2023)
Margalit Glasgow
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem. CoRR (2023)
Arvind Mahankali, Jeff Z. HaoChen, Kefan Dong, Margalit Glasgow, Tengyu Ma
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. CoRR (2023)
Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. CoRR (2022)
Alex Tamkin, Margalit Glasgow, Xiluo He, Noah D. Goodman
Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning. CoRR (2022)
Margalit Glasgow, Mary Wootters
Approximate Gradient Coding with Optimal Decoding. ISIT (2021)
Margalit Glasgow, Mary Wootters
Approximate Gradient Coding With Optimal Decoding. IEEE J. Sel. Areas Inf. Theory 2 (3) (2021)
Margalit Glasgow, Honglin Yuan, Tengyu Ma
Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. CoRR (2021)
Margalit Glasgow, Mary Wootters
Approximate Gradient Coding with Optimal Decoding. CoRR (2020)
Margalit Glasgow, Mary Wootters
Asynchronous Distributed Optimization with Randomized Delays. CoRR (2020)