Picture for Chao-Kai Chiang

Chao-Kai Chiang

Unified Risk Analysis for Weakly Supervised Learning

Add code
Sep 15, 2023
Viaarxiv icon

Asymptotically Optimal Thompson Sampling Based Policy for the Uniform Bandits and the Gaussian Bandits

Add code
Feb 28, 2023
Viaarxiv icon

Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits

Add code
Feb 03, 2023
Viaarxiv icon

Hyper-parameter Tuning under a Budget Constraint

Add code
Feb 01, 2019
Figure 1 for Hyper-parameter Tuning under a Budget Constraint
Figure 2 for Hyper-parameter Tuning under a Budget Constraint
Figure 3 for Hyper-parameter Tuning under a Budget Constraint
Figure 4 for Hyper-parameter Tuning under a Budget Constraint
Viaarxiv icon

Federated Multi-Task Learning

Add code
Feb 27, 2018
Figure 1 for Federated Multi-Task Learning
Figure 2 for Federated Multi-Task Learning
Figure 3 for Federated Multi-Task Learning
Figure 4 for Federated Multi-Task Learning
Viaarxiv icon

An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits

Add code
May 27, 2016
Viaarxiv icon