◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Maksim Velikanov

15 papers hereh-index 9195 citations17 works total

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

author position
  • first author7
  • middle author6
  • last author1

Across the 14 of 15 papers where every author was matched, so the position is known.

fields
  • cs.LG6
  • cs.CL3
  • cond-mat.str-el2
  • stat.ML2
  • cs.CV1
  • math.OC1

identity via Semantic Scholar / OpenAlex

activity
20182026
most citedUniversal scaling laws in the gradient descent training of neural networks

4 citations · 12 across the 13 of their papers we have counts for

collaborators
Showing 2022Show all

3 papers · 1 filter

cs.LG2022

A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta

Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky

Mini-batch SGD with momentum is a fundamental algorithm for learning large predictive models. In this paper we develop a new analytic framework to analyze noise-averaged properties…

stat.ML2022

Embedded Ensembles: Infinite Width Limit and Operating Regimes

Maksim Velikanov, Roman Kail, Ivan Anokhin +4

A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as E…

math.OC2022★ 1 cited

Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions

Maksim Velikanov, Dmitry Yarotsky

Performance of optimization on quadratic problems sensitively depends on the low-lying part of the spectrum. For large (effectively infinite-dimensional) problems, this part of the…

◍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.