Reza Gheissari
4 papers · 2021–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Venues
Top co-authors
Research topics
Keywords
stochastic gradient descent
(4)
neural network training
(1)
online learning
(1)
non-convex optimization
(1)
parameter estimation
(1)
high-dimensional inference
(1)
high-dimensional statistics
(1)
high-dimensional analysis
(1)
hessian matrix
(1)
phase retrieval
(1)
eigenvalue analysis
(1)
generalized linear model
(1)
gradient flow
(1)
stochastic differential equation
(1)
cross-entropy loss
(1)
ordinary differential equation
(1)
high-dimensional classification
(1)
gaussian mixture distribution
(1)
high-dimensional limit theorem
(1)
effective dynamics
(1)
Papers
Universality of high-dimensional scaling limits of stochastic gradient descent (extended abstract)
COLT 2026
High-dimensional SGD aligns with emerging outlier eigenspaces
ICLR 2024
High-dimensional limit theorems for SGD: Effective dynamics and critical scaling
NeurIPS 2022
Online stochastic gradient descent on non-convex losses from high-dimensional inference
JMLR 2021