Aukosh Jagannath
10 papers · 2021–2026 · 5 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (22)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(57)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory
(7)
Deep Learning
(6)
Mathematics & Optimization
(5)
Architectures
(4)
Core Methods
(4)
Application Areas
(2)
Mathematics
(2)
Optimization
(2)
Artificial Intelligence
(1)
Security & Privacy
(1)
Bayesian & Probabilistic
(1)
Differential Privacy
(1)
Learning Paradigms
(1)
Learning Types
(1)
Keywords
stochastic gradient descent
(4)
stochastic block model
(3)
node classification
(3)
graph neural network
(2)
high-dimensional inference
(1)
transfer learning
(1)
non-convex optimization
(1)
attention mechanism
(1)
online learning
(1)
sample complexity
(1)
parameter estimation
(1)
out-of-distribution generalization
(1)
theoretical analysis
(1)
high-dimensional statistics
(1)
generalization error
(1)
message passing
(1)
high-dimensional analysis
(1)
semi-supervised classification
(1)
robust estimation
(1)
unsupervised pretraining
(1)
Papers
Universality of high-dimensional scaling limits of stochastic gradient descent (extended abstract)
COLT 2026
Differentially Private Multivariate Medians
JMLR 2025
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
ICML 2025
High-dimensional SGD aligns with emerging outlier eigenspaces
ICLR 2024
Effects of Graph Convolutions in Multi-layer Networks
ICLR 2023
Graph Attention Retrospective
JMLR 2023
Optimality of Message-Passing Architectures for Sparse Graphs
NeurIPS 2023
High-dimensional limit theorems for SGD: Effective dynamics and critical scaling
NeurIPS 2022
Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization
ICML 2021
Online stochastic gradient descent on non-convex losses from high-dimensional inference
JMLR 2021