◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Pengcheng Cheng

4 papers hereh-index 13 citations9 works total

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

author position
  • sole author2
  • middle author1
  • last author1

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.AI2
  • cs.LG1
  • stat.ML1

identity via Semantic Scholar / OpenAlex

works on
gradient flow 1implicit bias 1positive quadratic networks 1quotient manifold 1spectral initialization 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

Quotient Dynamics, Effective Curvature, and Implicit Bias in Positive Quadratic Networks

Pengcheng Cheng

The paper studies how the quotient structure of positive quadratic networks influences training dynamics, curvature, recovery guarantees, and implicit bias, providing exact gradien…

cs.AI2026

Gauge-Equivariant Intrinsic Neural Operators for Geometry-Consistent Learning of Elliptic PDE Maps

Pengcheng Cheng

Learning solution operators of partial differential equations (PDEs) from data has emerged as a promising route to fast surrogate models in multi-query scientific workflows. Howeve…

◍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.