Picture for Yanjun Han

Yanjun Han

Online Estimation via Offline Estimation: An Information-Theoretic Framework

Apr 15, 2024
Viaarxiv icon

Stochastic contextual bandits with graph feedback: from independence number to MAS number

Feb 12, 2024
Viaarxiv icon

Covariance alignment: from maximum likelihood estimation to Gromov-Wasserstein

Nov 22, 2023
Figure 1 for Covariance alignment: from maximum likelihood estimation to Gromov-Wasserstein
Figure 2 for Covariance alignment: from maximum likelihood estimation to Gromov-Wasserstein
Viaarxiv icon

Online Learning in Multi-unit Auctions

May 27, 2023
Figure 1 for Online Learning in Multi-unit Auctions
Viaarxiv icon

Beyond UCB: Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits

Feb 12, 2023
Figure 1 for Beyond UCB: Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
Figure 2 for Beyond UCB: Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
Viaarxiv icon

Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient

Jan 19, 2023
Figure 1 for Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
Viaarxiv icon

Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions

Nov 05, 2022
Figure 1 for Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
Figure 2 for Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
Figure 3 for Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
Figure 4 for Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions
Viaarxiv icon

Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits

Nov 01, 2022
Figure 1 for Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits
Figure 2 for Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits
Figure 3 for Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits
Figure 4 for Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits
Viaarxiv icon

Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries

Mar 08, 2022
Figure 1 for Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries
Viaarxiv icon

On the Statistical Complexity of Sample Amplification

Jan 12, 2022
Figure 1 for On the Statistical Complexity of Sample Amplification
Viaarxiv icon