Jikai Jin
9 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (21)
π
Cross-Pollinator
(3)
π
Renaissance Researcher
(5)
π₯
Unstoppable
(6)
Conferences
NIPS (4)
COLT (2)
ICLR (2)
ICML (1)
Top co-authors
Keywords
non-convex optimization
(2)
convergence analysis
(2)
gradient descent
(2)
stochastic gradient descent
(1)
adversarial robustness
(1)
incremental learning
(1)
vc dimension
(1)
low-rank recovery
(1)
low-rank representation
(1)
expressive power
(1)
distributionally robust optimization
(1)
latent variable model
(1)
latent variable
(1)
conditional value-at-risk
(1)
matrix sensing
(1)
implicit bia
(1)
gradient clipping
(1)
causal representation learning
(1)
adversarial example
(1)
linear causal model
(1)
Papers
Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation (Extended Abstract)
COLT 2025
Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
NIPS 2024
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
ICLR 2024
Minimax Optimal Kernel Operator Learning via Multilevel Training
ICLR 2023
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
ICML 2023
Understanding Riemannian Acceleration via a Proximal Extragradient Framework
COLT 2022
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
NIPS 2022
Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis
NIPS 2021
Improved Analysis of Clipping Algorithms for Non-convex Optimization
NIPS 2020