activity
20182022
most citedChoosing the Sample with Lowest Loss makes SGD Robust

11 citations · 22 across the 6 of their papers we have counts for

collaborators

11 papers

cs.LG20224 cited

Toward Understanding Privileged Features Distillation in Learning-to-Rank

Shuo Yang, Sujay Sanghavi, Holakou Rahmanian +2

In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised rec…

cs.LG2021

Combinatorial Bandits without Total Order for Arms

Shuo Yang, Tongzheng Ren, Inderjit S. Dhillon +1

We consider the combinatorial bandits problem, where at each time step, the online learner selects a size- subset from the arms set , where $\left|\mathcal{A}\r…

stat.ML2020

Faster Non-Convex Federated Learning via Global and Local Momentum

Rudrajit Das, Anish Acharya, Abolfazl Hashemi +3

We propose \texttt{FedGLOMO}, a novel federated learning (FL) algorithm with an iteration complexity of to converge to an -stationary point (i.e., $\math…

stat.ML2020

On Generalization of Adaptive Methods for Over-parameterized Linear Regression

Vatsal Shah, Soumya Basu, Anastasios Kyrillidis +1

Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us…

cs.LG20205 cited

On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization

Abolfazl Hashemi, Anish Acharya, Rudrajit Das +3

In decentralized optimization, it is common algorithmic practice to have nodes interleave (local) gradient descent iterations with gossip (i.e. averaging over the network) steps. M…

cs.LG2020

Extreme Multi-label Classification from Aggregated Labels

Yanyao Shen, Hsiang-fu Yu, Sujay Sanghavi +1

Extreme multi-label classification (XMC) is the problem of finding the relevant labels for an input, from a very large universe of possible labels. We consider XMC in the setting w…