Publications

Full list, most recent first. Click a title for abstract + BibTeX.

2026

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
Jikai Jin, Vasilis Syrgkanis, Sham Kakade, Hanlin Zhang
In COLM 2026
PDF cite ArXiv
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham Kakade
In ICML 2026 (oral, top 0.7%)
PDF DOI ArXiv Blog Dataset
Adaptive Exploration for Latent-State Bandits
Jikai Jin, Kenneth Hung, Sanath Kumar Krishnamurthy, Baoyi Shi, Congshan Zhang
In KDD 2026
cite DOI ArXiv
Policy Learning with Abstention
Ayush Sawarni, Jikai Jin, Justin Whitehouse, Vasilis Syrgkanis
In AISTATS 2026
cite ArXiv

2025

Sharp Structure-Agnostic Lower Bounds for General Linear Functional Estimation
Jikai Jin, Vasilis Syrgkanis
arXiv
cite DOI ArXiv
It's Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation
Jikai Jin, Lester Mackey, Vasilis Syrgkanis
In NeurIPS 2025
ArXiv
Solving Inequality Proofs with Large Language Models
Jiayi Sheng, Luna Lyu, Jikai Jin, Tony Xia, Alex Gu, James Zou, Pan Lu
In NeurIPS 2025 (Datasets and Benchmarks track, spotlight)
PDF cite ArXiv Website Twitter
Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation
Jikai Jin, Vasilis Syrgkanis
In COLT 2025
cite ArXiv Poster Slides Blog

2024

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon S. Du, Jason D. Lee, Wei Hu
In ICLR 2024
cite ArXiv
Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
Jikai Jin, Vasilis Syrgkanis
In NeurIPS 2024 (spotlight)
cite ArXiv Slides

2023

Minimax Optimal Kernel Operator Learning via Multilevel Training
Jikai Jin, Yiping Lu, Jose Blanchet, Lexing Ying
In ICLR 2023 (spotlight)
PDF cite ArXiv Slides Poster
Understanding Incremental Learning of Gradient Descent -- A Fine-grained Analysis of Matrix Sensing
Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee
In ICML 2023
PDF cite ArXiv Poster Slides

2022

Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
Binghui Li, Jikai Jin, Han Zhong, John E. Hopcroft, Liwei Wang
In NeurIPS 2022
PDF cite ArXiv
Understanding Riemannian Acceleration via a Proximal Extragradient Framework
Jikai Jin, Suvrit Sra
In COLT 2022
PDF cite ArXiv

2021

Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis
Jikai Jin, Bohang Zhang, Haiyang Wang, Liwei Wang
In NeurIPS 2021
PDF cite ArXiv

2020

Improved analysis of clipping algorithms for non-convex optimization
Bohang Zhang, Jikai Jin, Cong Fang, Liwei Wang
In NeurIPS 2020
PDF cite ArXiv