140 citations · 1.3k across the 125 of their papers we have counts for
9 papers · 1 filter
Pessimistic Off-Policy Multi-Objective Optimization
Shima Alizadeh, Aniruddha Bhargava, Karthick Gopalswamy +3
Multi-objective optimization is a type of decision making problems where multiple conflicting objectives are optimized. We study offline optimization of multi-objective policies fr…
Pre-trained Recommender Systems: A Causal Debiasing Perspective
Ziqian Lin, Hao Ding, Nghia Trong Hoang +3
Recent studies on pre-trained vision/language models have demonstrated the practical benefit of a new, promising solution-building paradigm in AI where models can be pre-trained on…
Efficient and Interpretable Bandit Algorithms
Subhojyoti Mukherjee, Ruihao Zhu, Branislav Kveton
Motivated by the importance of explainability in modern machine learning, we design bandit algorithms that are efficient and interpretable. A bandit algorithm is interpretable if i…
Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances
Anusha Lalitha, Kousha Kalantari, Yifei Ma +2
We study the problem of best-arm identification (BAI) in the fixed-budget setting with heterogeneous reward variances. We propose two variance-adaptive BAI algorithms for this sett…
Finite-Time Logarithmic Bayes Regret Upper Bounds
Alexia Atsidakou, Branislav Kveton, Sumeet Katariya +2
We derive the first finite-time logarithmic Bayes regret upper bounds for Bayesian bandits. In a multi-armed bandit, we obtain and upper bounds for…
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
Aadirupa Saha, Branislav Kveton
Most bandit algorithms assume that the reward variances or their upper bounds are known, and that they are the same for all arms. This naturally leads to suboptimal performance and…