Tianyuan Jin

12 papers · 2019–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🐝 Cross-Pollinator (10) 🗺️ Taxonomy Completionist (18) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🏃 Academic Marathon (6) 🏆 Grand Slam 💎 Century Club (12) 🔥 Unstoppable (5)

Conferences

ICML (5) NIPS (4) AAAI (1) COLT (1) ICLR (1)

Top co-authors

Xiaokui Xiao (8) Pan Xu (8) Jing Tang (3) Quanquan Gu (3) Jieming SHI (2) Keke Huang (2) Nicolò Cesa-bianchi (1) Yu Yang (1) Enhong Chen (1) Qin Zhang (1)

Keywords

multi-armed bandit (10) regret bound (6) thompson sampling (4) minimax optimality (2) sample complexity (2) best arm identification (2) bayesian inference (2) batch complexity (2) pac learning (1) exponential family (1) bayesian learning (1) exponential families (1) query complexity (1) bayesian optimization (1) posterior distribution (1) regret minimization (1) asymptotic optimality (1) batch algorithms (1) adaptive sampling (1) posterior sampling (1)

Papers

Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids ICLR 2025

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries NIPS 2024

Optimal Batched Best Arm Identification NIPS 2024

Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs AAAI 2024

Optimal Batched Linear Bandits ICML 2024

Thompson Sampling with Less Exploration is Fast and Optimal ICML 2023

Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits NIPS 2022

Double Explore-then-Commit: Asymptotic Optimality and Beyond COLT 2021

MOTS: Minimax Optimal Thompson Sampling ICML 2021

Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits ICML 2021

Optimal Streaming Algorithms for Multi-Armed Bandits ICML 2021

Efficient Pure Exploration in Adaptive Round model NIPS 2019