◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Sujay Sanghavi

30 papers hereh-index 201.6k citations57 works total

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

author position
  • first author1
  • middle author16
  • last author12

Across the 29 of 30 papers where every author was matched, so the position is known.

fields
  • cs.LG23
  • stat.ML5
  • cs.CL1
  • math.NA1
same name
  • Sujay Sanghavi — 17 papers, h 6
  • Sujay Sanghavi — 7 papers, h 1

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20112025
most citedClustering Partially Observed Graphs via Convex Optimization

94 citations · 301 across the 30 of their papers we have counts for

collaborators
Showing 2019Show all

4 papers · 1 filter

cs.LG2019★ 2 cited

Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space

Shuo Yang, Yanyao Shen, Sujay Sanghavi

Quadratic regression involves modeling the response as a (generalized) linear function of not only the features xj1​ but also of quadratic terms xj1​xj2​. The inclusio…

cs.LG2019★ 8 cited

Learning Distributions Generated by One-Layer ReLU Networks

Shanshan Wu, Alexandros G. Dimakis, Sujay Sanghavi

We consider the problem of estimating the parameters of a d-dimensional rectified Gaussian distribution from i.i.d. samples. A rectified Gaussian distribution is defined by passi…

cs.LG2019★ 9 cited

Blocking Bandits

Soumya Basu, Rajat Sen, Sujay Sanghavi +1

We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusi…

cs.LG2019★ 53 cited

PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration

Sangkug Lym, Esha Choukse, Siavash Zangeneh +3

State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resourc…

◍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.