◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Daniel M. Roy

University of Toronto

29 papers hereh-index 398.9k citations117 works total

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

author position
  • middle author12
  • last author14

Across the 26 of 29 papers where every author was matched, so the position is known.

fields
  • cs.LG15
  • stat.ML9
  • cs.PL3
  • math.LO1
  • math.PR1
affiliations
  • University of Toronto
  • Vector Institute
HomepageORCID 0000-0001-8930-0058
same name
  • Daniel M. Roy — 9 papers
  • Daniel M. Roy — 7 papers, h 6
  • Daniel M. Roy — 2 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
20092023
most citedTraining generative neural networks via Maximum Mean Discrepancy optimization

183 citations · 387 across the 16 of their papers we have counts for

collaborators
Showing 2021Show all

3 papers · 1 filter

stat.ML2021

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers

Jeffrey Negrea, Blair Bilodeau, Nicolò Campolongo +2

Quantile (and, more generally, KL) regret bounds, such as those achieved by NormalHedge (Chaudhuri, Freund, and Hsu 2009) and its variants, relax the goal of competing against the…

stat.ML2021★ 2 cited

The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization

Mufan Bill Li, Mihai Nica, Daniel M. Roy

Theoretical results show that neural networks can be approximated by Gaussian processes in the infinite-width limit. However, for fully connected networks, it has been previously s…

cs.LG2021

NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization

Ali Ramezani-Kebrya, Fartash Faghri, Ilya Markov +3

As the size and complexity of models and datasets grow, so does the need for communication-efficient variants of stochastic gradient descent that can be deployed to perform paralle…

◍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.