◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Sharan Vaswani

16 papers hereh-index 171.5k citations60 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author3
  • middle author2
  • last author10

Across the 15 of 16 papers where every author was matched, so the position is known.

fields
  • cs.LG13
  • math.OC3

identity via Semantic Scholar / OpenAlex

activity
20242026
most citedTowards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing math.OCShow all

3 papers · 1 filter

math.OC2026

Glocal Smoothness: Line search and adaptive step sizes can help in theory too!

Curtis Fox, Aaron Mishkin, Sharan Vaswani +1

Iteration complexities for optimizing smooth functions with first-order algorithms are typically stated in terms of a global Lipschitz constant of the gradient, and near-optimal re…

math.OC2026★ 1 cited

Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent

Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad

We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise I¨ƒ2 in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly…

math.OC2025

(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum

Anh Dang, Reza Babanezhad, Sharan Vaswani

Stochastic heavy ball momentum (SHB) is commonly used to train machine learning models, and often provides empirical improvements over stochastic gradient descent. By primarily foc…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.