Peizhong Ju
14 papers · 2020–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Cross-Pollinator (9) π Conference Polyglot (4) π£ Hot Topic Early Bird π Academic Marathon (5) π Interdisciplinary Bridge
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(16)
π€
Dynamic Duo
(10)
π
Grand Slam
β
The Questioner
β‘
Prolific Year
(6)
π
Century Club
(13)
π₯
Unstoppable
(6)
Conferences
ICLR (6)
ICML (4)
NIPS (2)
AAAI (1)
EACL (1)
Top co-authors
Keywords
generalization error
(3)
double descent
(2)
learning theory
(2)
gradient descent
(2)
neural tangent kernel
(2)
convergence analysis
(1)
computational complexity
(1)
linear regression
(1)
sparse linear regression
(1)
multi-objective optimization
(1)
basis pursuit
(1)
generalization bound
(1)
convergence rate
(1)
relu activation
(1)
sparse autoencoder
(1)
two-layer neural network
(1)
task similarity
(1)
backpropagation complexity
(1)
concept activation
(1)
jensen-shannon distance
(1)
Papers
Evaluating Sparse Autoencoders for Monosemantic Representation
EACL 2026
PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization
AAAI 2025
Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
ICLR 2025
How to Find the Exact Pareto Front for Multi-Objective MDPs?
ICLR 2025
Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
ICLR 2025
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
ICML 2025
FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation
ICML 2025
Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
ICLR 2024
Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
ICLR 2024
Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
ICLR 2023
Theory on Forgetting and Generalization of Continual Learning
ICML 2023
On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model
NIPS 2022
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
ICML 2021
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
NIPS 2020