◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

A. Gholami

51 papers hereh-index 4411.6k citations84 works total

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

author position
  • first author6
  • middle author29
  • last author10

Across the 45 of 51 papers where every author was matched, so the position is known.

fields
  • cs.LG20
  • cs.CL14
  • cs.CV8
  • cs.DC2
  • eess.AS2
  • math.OC2
same name
  • A. Gholami — 32 papers, h 26
  • A. Gholami — 11 papers, h 5
  • A. Gholami — 10 papers, h 14
  • A. Gholami — 7 papers, h 24
  • A. Gholami — 4 papers, h 24
  • A. Gholami — 4 papers, h 6

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
20162024
most citedCharacterizing possible failure modes in physics-informed neural networks

118 citations · 511 across the 21 of their papers we have counts for

collaborators
Showing 2018 · cs.LGShow all

4 papers · 2 filters

cs.LG2018

Trust Region Based Adversarial Attack on Neural Networks

Zhewei Yao, Amir Gholami, Peng Xu +2

Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tu…

cs.LG2018

Parameter Re-Initialization through Cyclical Batch Size Schedules

Norman Mu, Zhewei Yao, Amir Gholami +2

Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutio…

cs.LG2018

On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent

Noah Golmant, Nikita Vemuri, Zhewei Yao +5

Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and syste…

cs.LG2018

Large batch size training of neural networks with adversarial training and second-order information

Zhewei Yao, Amir Gholami, Daiyaan Arfeen +4

The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep…

◍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.