Search Results for author:
Found 8 papers, 1 papers with code
Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
In this paper, we establish a sufficient condition for perturbations to achieve $\mathcal{O}(\sqrt{KT})$ regrets in the adversarial setting, which covers, e. g., Fr\'{e}chet, Pareto, and Student-$t$ distributions.
Thompson Exploration with Best Challenger Rule in Best Arm Identification
This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit framework in the canonical single-parameter exponential models.
The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models
Although the uniform prior is shown to be optimal, we highlight the inherent limitation of its optimality, which is limited to specific parameterizations and emphasizes the significance of the invariance property of priors.
Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
In addition to the empirical performance, TS has been shown to achieve asymptotic problem-dependent lower bounds in several models.
A Symmetric Loss Perspective of Reliable Machine Learning
When minimizing the empirical risk in binary classification, it is a common practice to replace the zero-one loss with a surrogate loss to make the learning objective feasible to optimize.
Learning Only from Relevant Keywords and Unlabeled Documents
We consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given.
Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation
Appropriately evaluating the discrepancy between domains is essential for the success of unsupervised domain adaptation.
On Symmetric Losses for Learning from Corrupted Labels
This paper aims to provide a better understanding of a symmetric loss.
