Search Results - "Glasgow, Margalit"

Determination of RNA structural diversity and its role in HIV-1 RNA splicing by Tomezsko, Phillip J., Corbin, Vincent D. A., Gupta, Paromita, Swaminathan, Harish, Glasgow, Margalit, Persad, Sitara, Edwards, Matthew D., Mcintosh, Lachlan, Papenfuss, Anthony T., Emery, Ann, Swanstrom, Ronald, Zang, Trinity, Lan, Tammy C. T., Bieniasz, Paul, Kuritzkes, Daniel R., Tsibris, Athe, Rouskin, Silvi

“…Human immunodeficiency virus 1 (HIV-1) is a retrovirus with a ten-kilobase single-stranded RNA genome. HIV-1 must express all of its gene products from a…”
Get full text

Approximate Gradient Coding With Optimal Decoding by Glasgow, Margalit, Wootters, Mary

“…Gradient codes use data replication to mitigate the effect of straggling machines in distributed machine learning. Approximate gradient codes consider codes…”
Get full text

On the rank, Kernel, and core of sparse random graphs by DeMichele, Patrick, Glasgow, Margalit, Moreira, Alexander

“…We study the rank of the adjacency matrix A$$ A $$ of a random Erdős‐Rényi graph G∼𝔾(n,p). It is well known that when p=(log(n)−ω(1))/n$$ p=\left(\log…”
Get full text

Feature Learning in Neural Networks and Other Stochastic Explorations by Glasgow, Margalit

“…Recent years have empirically demonstrated the unprecedented success of deep learning. Yet our theoretical understanding of why gradient descent succeeds in…”
Get full text

SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem by Glasgow, Margalit

“…In this work, we consider the optimization process of minibatch stochastic gradient descent (SGD) on a 2-layer neural network with data separated by a…”
Get full text

Author Correction: Determination of RNA structural diversity and its role in HIV-1 RNA splicing by Tomezsko, Phillip J., Corbin, Vincent D. A., Gupta, Paromita, Swaminathan, Harish, Glasgow, Margalit, Persad, Sitara, Edwards, Matthew D., Mcintosh, Lachlan, Papenfuss, Anthony T., Emery, Ann, Swanstrom, Ronald, Zang, Trinity, Lan, Tammy C. T., Bieniasz, Paul, Kuritzkes, Daniel R., Tsibris, Athe, Rouskin, Silvi

“…An amendment to this paper has been published and can be accessed via a link at the top of the paper…”
Get full text

Convergence of Distributed Adaptive Optimization with Local Updates by Cheng, Ziheng, Glasgow, Margalit

“…We study distributed adaptive algorithms with local updates (intermittent communication). Despite the great empirical success of adaptive methods in…”
Get full text

Invertibility of the 3-core of Erdos Renyi Graphs with Growing Degree by Glasgow, Margalit

“…Let $A \in \mathbb{R}^{n \times n}$ be the adjacency matrix of an Erd\H{o}s R\'enyi graph $G(n, d/n)$ for $d = \omega(1)$ and $d \leq 3\log(n)$. We show that…”
Get full text

Tight Bounds for $\gamma$-Regret via the Decision-Estimation Coefficient by Glasgow, Margalit, Rakhlin, Alexander

“…In this work, we give a statistical characterization of the $\gamma$-regret for arbitrary structured bandit problems, the regret which arises when comparing…”
Get full text

Approximate Gradient Coding with Optimal Decoding by Glasgow, Margalit, Wootters, Mary

“…In distributed optimization problems, a technique called gradient coding, which involves replicating data points, has been used to mitigate the effect of…”
Get full text

Approximate Gradient Coding with Optimal Decoding by Glasgow, Margalit, Wootters, Mary

“…In distributed optimization problems, a technique called gradient coding, which involves replicating data points, has been used to mitigate the effect of…”
Get full text

Asynchronous Distributed Optimization with Stochastic Delays by Glasgow, Margalit, Wootters, Mary

“…We study asynchronous finite sum minimization in a distributed-data setting with a central parameter server. While asynchrony is well understood in parallel…”
Get full text

A central limit theorem for the matching number of a sparse random graph by Glasgow, Margalit, Kwan, Matthew, Sah, Ashwin, Sawhney, Mehtaab

“…In 1981, Karp and Sipser proved a law of large numbers for the matching number of a sparse Erd\H{o}s-R\'enyi random graph, in an influential paper pioneering…”
Get full text

Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective by Glasgow, Margalit, Yuan, Honglin, Ma, Tengyu

“…Federated Averaging (FedAvg), also known as Local SGD, is one of the most popular algorithms in Federated Learning (FL). Despite its simplicity and popularity,…”
Get full text

The Exact Rank of Sparse Random Graphs by Glasgow, Margalit, Kwan, Matthew, Sah, Ashwin, Sawhney, Mehtaab

“…Two landmark results in combinatorial random matrix theory, due to Koml\'os and Costello-Tao-Vu, show that discrete random matrices and symmetric discrete…”
Get full text

On the Rank, Kernel, and Core of Sparse Random Graphs by DeMichele, Patrick, Glasgow, Margalit, Moreira, Alexander

“…We study the rank of the adjacency matrix $A$ of a random Erdos Renyi graph $G\sim \mathbb{G}(n,p)$. It is well known that when $p = (\log(n) - \omega(1))/n$,…”
Get full text

Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning by Tamkin, Alex, Glasgow, Margalit, He, Xiluo, Goodman, Noah

“…What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific…”
Get full text

Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence by Glasgow, Margalit, Wei, Colin, Wootters, Mary, Ma, Tengyu

“…A major challenge in modern machine learning is theoretically understanding the generalization properties of overparameterized models. Many existing tools rely…”
Get full text

The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication by Patel, Kumar Kshitij, Glasgow, Margalit, Zindari, Ali, Wang, Lingxiao, Stich, Sebastian U, Cheng, Ziheng, Joshi, Nirmit, Srebro, Nathan

“…Local SGD is a popular optimization method in distributed learning, often outperforming other algorithms in practice, including mini-batch SGD. Despite this…”
Get full text

Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time by Mahankali, Arvind, Haochen, Jeff Z, Dong, Kefan, Glasgow, Margalit, Ma, Tengyu

“…Despite recent theoretical progress on the non-convex optimization of two-layer neural networks, it is still an open question whether gradient descent on…”
Get full text