Khashayar Gatmiry
16 papers · 2020–2025 · 6 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 ↑
🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (31) 🌍 Conference Polyglot · Silver 🗃️ Keyword Collector (94)
❓
The Questioner
(3)
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(15)
Optimization & Theory · Machine Learning
(15)
Deep Learning
(8)
Mathematics & Optimization
(7)
Optimization
(7)
Optimization & Theory · Deep Learning
(5)
Architectures
(4)
Bayesian & Probabilistic · Machine Learning
(4)
Core Methods
(3)
Artificial Intelligence
(2)
Learning Types
(2)
Mathematics
(2)
Models
(2)
Bayesian & Probabilistic · Artificial Intelligence
(1)
Learning Paradigms
(1)
Keywords
generalization bound
(3)
self-concordant barrier
(2)
diffusion model
(2)
gradient descent
(2)
stochastic gradient descent
(2)
online convex optimization
(2)
regret bound
(2)
feature extraction
(1)
distributed learning
(1)
probabilistic modeling
(1)
expectation maximization
(1)
computational complexity
(1)
theoretical analysis
(1)
markov chain monte carlo
(1)
sample complexity
(1)
online learning
(1)
convergence
(1)
in-context learning
(1)
linear regression
(1)
algorithmic stability
(1)
Papers
Computing Optimal Regularizers for Online Linear Optimization
COLT 2025
Learning Mixtures of Gaussians Using Diffusion Models
COLT 2025
Rethinking Invariance in In-context Learning
ICLR 2025
Adversarial Online Learning with Temporal Feedback Graphs
COLT 2024
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
ICML 2024
EM for Mixture of Linear Regression with Clustered Data
AISTATS 2024
Sampling Polytopes with Riemannian HMC: Faster Mixing via the Lewis Weights Barrier
COLT 2024
Simplicity Bias via Global Convergence of Sharpness Minimization
ICML 2024
What does guidance do? A fine-grained analysis in a simple setting
NeurIPS 2024
A Unified Approach to Controlling Implicit Regularization via Mirror Descent
JMLR 2023
Projection-Free Online Convex Optimization via Efficient Newton Iterations
NeurIPS 2023
Quasi-Newton Steps for Efficient Online Exp-Concave Optimization
COLT 2023
What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models
NeurIPS 2023
On the generalization of learning algorithms that do not converge
NeurIPS 2022
Optimization and Adaptive Generalization of Three layer Neural Networks
ICLR 2022
Testing Determinantal Point Processes
NeurIPS 2020