◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Siyuan Ma

11 papers hereh-index 134.6k citations41 works total

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

author position
  • first author4
  • middle author5
  • last author1

Across the 10 of 11 papers where every author was matched, so the position is known.

fields
  • cs.CV3
  • cs.AI2
  • cs.LG2
  • stat.ML2
  • cs.AR1
  • math.OC1
same name
  • Siyuan Ma — 4 papers, h 8
  • Siyuan Ma — 4 papers, h 5
  • Siyuan Ma — 2 papers
  • Siyuan Ma — 2 papers, h 18
  • Siyuan Ma — 2 papers
  • Siyuan Ma — 1 paper, h 5

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
20182026
collaborators
Showing stat.MLShow all

2 papers · 1 filter

stat.ML2024

Fast training of large kernel models with delayed projections

Amirhesam Abedsoltan, Siyuan Ma, Parthe Pandit +1

Classical kernel machines have historically faced significant challenges in scaling to large datasets and model sizes--a key ingredient that has driven the success of neural networ…

stat.ML2018

Kernel machines that adapt to GPUs for effective large batch training

Siyuan Ma, Mikhail Belkin

Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a…

◍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.