Picture for Parnian Kassraie

Parnian Kassraie

Bandits with Preference Feedback: A Stackelberg Game Perspective

Add code
Jun 24, 2024
Viaarxiv icon

Progressive Entropic Optimal Transport Solvers

Add code
Jun 07, 2024
Viaarxiv icon

Anytime Model Selection in Linear Bandits

Add code
Jul 24, 2023
Viaarxiv icon

Hallucinated Adversarial Control for Conservative Offline Policy Evaluation

Add code
Mar 02, 2023
Figure 1 for Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
Figure 2 for Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
Figure 3 for Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
Figure 4 for Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
Viaarxiv icon

Instance-Dependent Generalization Bounds via Optimal Transport

Add code
Nov 07, 2022
Viaarxiv icon

Lifelong Bandit Optimization: No Prior and No Regret

Add code
Oct 27, 2022
Viaarxiv icon

Graph Neural Network Bandits

Add code
Jul 13, 2022
Figure 1 for Graph Neural Network Bandits
Figure 2 for Graph Neural Network Bandits
Figure 3 for Graph Neural Network Bandits
Figure 4 for Graph Neural Network Bandits
Viaarxiv icon

Meta-Learning Hypothesis Spaces for Sequential Decision-making

Add code
Feb 01, 2022
Figure 1 for Meta-Learning Hypothesis Spaces for Sequential Decision-making
Figure 2 for Meta-Learning Hypothesis Spaces for Sequential Decision-making
Figure 3 for Meta-Learning Hypothesis Spaces for Sequential Decision-making
Figure 4 for Meta-Learning Hypothesis Spaces for Sequential Decision-making
Viaarxiv icon

Neural Contextual Bandits without Regret

Add code
Jul 07, 2021
Figure 1 for Neural Contextual Bandits without Regret
Figure 2 for Neural Contextual Bandits without Regret
Figure 3 for Neural Contextual Bandits without Regret
Figure 4 for Neural Contextual Bandits without Regret
Viaarxiv icon