Search Results for author:
Found 17 papers, 6 papers with code
Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) to human preferences at the time of decoding.
Return-Aligned Decision Transformer
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return.
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding
Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks.
Model-Based Minimum Bayes Risk Decoding
MBR decoding selects a hypothesis from a pool of hypotheses that has the least expected risk under a probability model according to a given utility function.
On Uniformly Optimal Algorithms for Best Arm Identification in Two-Armed Bandits with Fixed Budget
We prove that there is no algorithm that (i) performs as well as the algorithm sampling each arm equally (this algorithm is referred to as the {\it uniform sampling} algorithm) on all instances, and that (ii) strictly outperforms this algorithm on at least one instance.
Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model
To this end, we revisit instance-specific lower bounds on the expected number of misclassified items satisfied by any clustering algorithm.
Slingshot Perturbation to Learning in Monotone Games
This paper addresses the problem of learning Nash equilibria in {\it monotone games} where the gradient of the payoff functions is monotone in the strategy profile space, potentially containing additive noise.
Exploration of Unranked Items in Safe Online Learning to Re-Rank
In this paper, we propose a safe OLTR algorithm that efficiently exchanges one of the items in the current ranking with an item outside the ranking (i. e., an unranked item) to perform exploration.
Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games
This paper proposes Mutation-Driven Multiplicative Weights Update (M2WU) for learning an equilibrium in two-player zero-sum normal-form games and proves that it exhibits the last-iterate convergence property in both full and noisy feedback settings.
Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap
We show that a strategy following the Neyman allocation rule (Neyman, 1934) is asymptotically optimal when the gap between the expected rewards is small.
Rate-optimal Bayesian Simple Regret in Best Arm Identification
We consider best arm identification in the multi-armed bandit problem.
Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling
We consider the "policy choice" problem -- otherwise known as best arm identification in the bandit literature -- proposed by Kasy and Sautmann (2021) for adaptive experimental design.
The Role of Contextual Information in Best Arm Identification
We demonstrate that contextual information can be used to improve the efficiency of the identification of the best marginalized mean reward compared with the results of Garivier & Kaufmann (2016).
Regret in Online Recommendation Systems
Interestingly, our analysis reveals the relative weights of the different components of regret: the component due to the constraint of not presenting the same item twice to the same user, that due to learning the chances users like items, and finally that arising when learning the underlying structure.
A Practical Guide of Off-Policy Evaluation for Bandit Problems
Based on the properties of the evaluation policy, we categorize OPE situations.
Thresholded Lasso Bandit
In this paper, we revisit the regret minimization problem in sparse stochastic contextual linear bandits, where feature vectors may be of large dimension $d$, but where the reward function depends on a few, say $s_0\ll d$, of these features only.
Optimal Clustering from Noisy Binary Feedback
The objective is to devise an algorithm with a minimal cluster recovery error rate.
