Search Results for author:
Found 29 papers, 8 papers with code
Best-of-Both-Worlds Algorithms for Partial Monitoring
To be more specific, we show that for non-degenerate locally observable games, the regret in the stochastic regime is bounded by $O(k^3 m^2 \log(T) \log(k_{\Pi} T) / \Delta_{\mathrm{\min}})$ and in the adversarial regime by $O(k^{2/3} m \sqrt{T \log(T) \log k_{\Pi}})$, where $T$ is the number of rounds, $m$ is the maximum number of distinct observations per action, $\Delta_{\min}$ is the minimum optimality gap, and $k_{\Pi}$ is the number of Pareto optimal actions.
Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
In fact, they have provided a stochastic MAB algorithm with gap-variance-dependent regret bounds of $O(\sum_{i: \Delta_i>0} (\frac{\sigma_i^2}{\Delta_i} + 1) \log T )$ for loss variance $\sigma_i^2$ of arm $i$.
Globally Optimal Algorithms for Fixed-Budget Best Arm Identification
We consider the fixed-budget best arm identification problem where the goal is to find the arm of the largest mean with a fixed number of samples.
The Survival Bandit Problem
We study the survival bandit problem, a variant of the multi-armed bandit problem introduced in an open problem by Perotto et al. (2019), with a constraint on the cumulative reward; at each time step, the agent receives a (possibly negative) reward and if the cumulative reward becomes lower than a prespecified threshold, the procedure stops, and this phenomenon is called ruin.
Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
As Alon et al. [2015] have shown, tight regret bounds depend on the structure of the feedback graph: \textit{strongly observable} graphs yield minimax regret of $\tilde{\Theta}( \alpha^{1/2} T^{1/2} )$, while \textit{weakly observable} graphs induce minimax regret of $\tilde{\Theta}( \delta^{1/3} T^{2/3} )$, where $\alpha$ and $\delta$, respectively, represent the independence number of the graph and the domination number of a certain portion of the graph.
Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits
We demonstrate that ADR-bandit has nearly optimal performance when the abrupt or global changes occur in a coordinated manner that we call global changes.
Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences
In this paper, we consider the task of predicting $Y$ from $X$ when we have no paired data of them, but we have two separate, independent datasets of $X$ and $Y$ each observed with some mediating variable $U$, that is, we have two datasets $S_X = \{(X_i, U_i)\}$ and $S_Y = \{(U'_j, Y'_j)\}$.
Combinatorial Pure Exploration with Full-bandit Feedback and Beyond: Solving Combinatorial Optimization under Uncertainty with Limited Observation
Combinatorial optimization is one of the fundamental research fields that has been extensively studied in theoretical computer science and operations research.
Online Dense Subgraph Discovery via Blurred-Graph Feedback
Dense subgraph discovery aims to find a dense component in edge-weighted graphs.
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback.
Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time
If the black-box function varies with time, then time-varying Bayesian optimization is a promising framework.
Efficient Adaptive Experimental Design for Average Treatment Effect Estimation
In adaptive experimental design, the experimenter is allowed to change the probability of assigning a treatment using past observations for estimating the ATE efficiently.
Uncoupled Regression from Pairwise Comparison Data
We propose two practical methods for uncoupled regression from pairwise comparison data and show that the learned regression model converges to the optimal model with the optimal parametric convergence rate when the target variable distributes uniformly.
Learning from Positive and Unlabeled Data with a Selection Bias
However, this assumption is unrealistic in many instances of PU learning because it fails to capture the existence of a selection bias in the labeling process.
A Note on KL-UCB+ Policy for the Stochastic Bandit
A classic setting of the stochastic K-armed bandit problem is considered in this note.
Polynomial-time Algorithms for Multiple-arm Identification with Full-bandit Feedback
Based on our approximation algorithm, we propose novel bandit algorithms for the top-k selection problem, and prove that our algorithms run in polynomial time.
A Bad Arm Existence Checking Problem
We study a bad arm existing checking problem in which a player's task is to judge whether a positive arm exists or not among given K arms by drawing as small number of arms as possible.
On the Calibration of Multiclass Classification with Rejection
First, we consider an approach based on simultaneous training of a classifier and a rejector, which achieves the state-of-the-art performance in the binary case.
Dueling Bandits with Qualitative Feedback
We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm.
Unsupervised Domain Adaptation Based on Source-guided Discrepancy
A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain.
Nonconvex Optimization for Regression with Fairness Constraints
However, a fairness level as a constraint induces a nonconvexity of the feasible region, which disables the use of an off-the-shelf convex optimizer.
Position-based Multiple-play Bandit Problem with Unknown Position Bias
Motivated by online advertising, we study a multiple-play multi-armed bandit problem with position bias that involves several slots and the latter slots yield fewer rewards.
Good Arm Identification via Bandit Feedback
We consider a novel stochastic multi-armed bandit problem called {\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold.
Fully adaptive algorithm for pure exploration in linear bandits
We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly.
Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm
We study the K-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms.
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring
To show the optimality of PM-DMED with respect to the regret bound, we slightly modify the algorithm by introducing a hinge function (PM-DMED-Hinge).
Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem
We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms.
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays
Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the standard single-play MAB problem.
Normal Bandits of Unknown Means and Variances: Asymptotic Optimality, Finite Horizon Regret Bounds, and a Solution to an Open Problem
Consider the problem of sampling sequentially from a finite number of $N \geq 2$ populations, specified by random variables $X^i_k$, $ i = 1,\ldots , N,$ and $k = 1, 2, \ldots$; where $X^i_k$ denotes the outcome from population $i$ the $k^{th}$ time it is sampled.
