Margalit Glasgow

21 papers A* 7B 1Journal 13

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Convergence of Distributed Adaptive Optimization with Local Updates. ICLR Ziheng Cheng, Margalit Glasgow
2025	A*	`conf`	Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon. COLT Margalit Glasgow, Denny Wu, Joan Bruna
2025	J	`jnl`	Propagation of Chaos in One-hidden-layer Neural Networks beyond Logarithmic Time. CoRR Margalit Glasgow, Denny Wu, Joan Bruna
2024	J	`jnl`	Convergence of Distributed Adaptive Optimization with Local Updates. CoRR Ziheng Cheng, Margalit Glasgow
2024	J	`jnl`	On the rank, Kernel, and core of sparse random graphs. Random Struct. Algorithms Patrick Demichele, Margalit Glasgow, Alexander Moreira
2024	A*	`conf`	SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem. ICLR Margalit Glasgow
2024	A*	`conf`	The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication. COLT Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
2024	J	`jnl`	The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication. CoRR Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U. Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro
2023	A*	`conf`	Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. NeurIPS Arvind V. Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma
2023	J	`jnl`	Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. CoRR Arvind V. Mahankali, Jeff Z. HaoChen, Kefan Dong, Margalit Glasgow, Tengyu Ma
2023	A*	`conf`	Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning. NeurIPS Alex Tamkin, Margalit Glasgow, Xiluo He, Noah D. Goodman
2023	J	`jnl`	Lower Bounds for γ-Regret via the Decision-Estimation Coefficient. CoRR Margalit Glasgow, Alexander Rakhlin
2023	A*	`conf`	Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. ICLR Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
2023	J	`jnl`	SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem. CoRR Margalit Glasgow
2022	J	`jnl`	Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning. CoRR Alex Tamkin, Margalit Glasgow, Xiluo He, Noah D. Goodman
2022	J	`jnl`	Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence. CoRR Margalit Glasgow, Colin Wei, Mary Wootters, Tengyu Ma
2021	J	`jnl`	Approximate Gradient Coding With Optimal Decoding. IEEE J. Sel. Areas Inf. Theory Margalit Glasgow, Mary Wootters
2021	B	`conf`	Approximate Gradient Coding with Optimal Decoding. ISIT Margalit Glasgow, Mary Wootters
2021	J	`jnl`	Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective. CoRR Margalit Glasgow, Honglin Yuan, Tengyu Ma
2020	J	`jnl`	Approximate Gradient Coding with Optimal Decoding. CoRR Margalit Glasgow, Mary Wootters
2020	J	`jnl`	Asynchronous Distributed Optimization with Randomized Delays. CoRR Margalit Glasgow, Mary Wootters