Behrad Moniri
6 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot (3) π Cross-Pollinator (12) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12)
π§
Keyword Pioneer
Conferences
ICML (4)
L4DC (1)
NAACL (1)
Top co-authors
Keywords
model evaluation
(2)
learning theory
(1)
domain generalization
(1)
bayesian learning
(1)
domain adaptation
(1)
distribution shift
(1)
classification error
(1)
generalization bound
(1)
generalization gap
(1)
information-theoretic bound
(1)
random features regression
(1)
large language model
(1)
minimum excess risk
(1)
information theory
(1)
parametric learning
(1)
Papers
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
ICML 2025
Asymptotics of Linear Regression with Linearly Dependent Data
L4DC 2025
Evaluating the Performance of Large Language Models via Debates
NAACL 2025
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
ICML 2024
Demystifying Disagreement-on-the-Line in High Dimensions
ICML 2023
Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
ICML 2021