◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Suriya Gunasekar

Microsoft Research

30 papers hereh-index 256k citations43 works total

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

author position
  • sole author1
  • first author10
  • middle author14
  • last author3

Across the 28 of 30 papers where every author was matched, so the position is known.

fields
  • cs.LG13
  • stat.ML10
  • cs.CL3
  • cs.CV3
  • stat.AP1
affiliations
  • Microsoft Research
  • Toyota Technological Institute at Chicago
Homepage
same name
  • Suriya Gunasekar — 1 paper, h 3

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
20142023
most citedCharacterizing Implicit Bias in Terms of Optimization Geometry

168 citations · 795 across the 28 of their papers we have counts for

collaborators
Showing 2018Show all

4 papers · 1 filter

cs.LG2018★ 17 cited

On preserving non-discrimination when combining expert advice

Avrim Blum, Suriya Gunasekar, Thodoris Lykouris +1

We study the interplay between sequential decision making and avoiding discrimination against protected groups, when examples arrive online and do not follow distributional assumpt…

cs.LG2018★ 35 cited

Implicit Bias of Gradient Descent on Linear Convolutional Networks

Suriya Gunasekar, Jason Lee, Daniel Soudry +1

We show that gradient descent on full-width linear convolutional networks of depth L converges to a linear predictor related to the ℓ2/L​ bridge penalty in the frequency d…

stat.ML2018★ 25 cited

Convergence of Gradient Descent on Separable Data

Mor Shpigel Nacson, Jason D. Lee, Suriya Gunasekar +3

We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets…

stat.ML2018★ 168 cited

Characterizing Implicit Bias in Terms of Optimization Geometry

Suriya Gunasekar, Jason Lee, Daniel Soudry +1

We study the implicit bias of generic optimization methods, such as mirror descent, natural gradient descent, and steepest descent with respect to different potentials and norms, w…

◍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.