activity
20182021
most citedNon-Gaussianity of Stochastic Gradient Noise

23 citations · 43 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG2021

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes

Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan +6

Learning binary representations of instances and classes is a classical problem with several high potential applications. In modern settings, the compression of high-dimensional ne…

cs.LG202112 cited

SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics

Jonathan Hayase, Weihao Kong, Raghav Somani +1

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is w…

cs.LG20206 cited

Robust Meta-learning for Mixed Linear Regression with Small Batches

Weihao Kong, Raghav Somani, Sham Kakade +1

A common challenge faced in practical supervised learning, such as medical image processing and robotic interactions, is that there are plenty of tasks but each task cannot afford…

cs.LG20202 cited

Meta-learning for mixed linear regression

Weihao Kong, Raghav Somani, Zhao Song +2

In modern supervised learning, there are a large number of tasks, but many of them are associated with only a small amount of labeled data. These include data from medical image pr…

cs.LG2020

Soft Threshold Weight Reparameterization for Learnable Sparsity

Aditya Kusupati, Vivek Ramanujan, Raghav Somani +4

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform…

cs.LG201923 cited

Non-Gaussianity of Stochastic Gradient Noise

Abhishek Panigrahi, Raghav Somani, Navin Goyal +1

What enables Stochastic Gradient Descent (SGD) to achieve better generalization than Gradient Descent (GD) in Neural Network training? This question has attracted much attention. I…