← Search

Prateek Varshney

2 accepted papers

2024

Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD

NeurIPS 2024poster

$\newcommand{\Tr}{\mathsf{Tr}}$ We consider the problem of high-dimensional heavy-tailed statistical estimation in the streaming setting, which is much harder than the traditional batch setting due to memory constraints. We cast this problem as stochastic convex optimization with heavy tailed stocha…

Cited by 2SourcePDFScholar
2024

Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components

AISTATS 2024poster

Personalization of machine learning (ML) predictions for individual users/domains/enterprises is critical for practical recommendation systems. Standard personalization approaches involve learning a user/domain specific \emph{embedding} that is fed into a fixed global model which can be limiting. On…

Cited by 1SourcePDFScholar