Search Results for author:
Found 31 papers, 0 papers with code
Online $\mathrm{L}^{\natural}$-Convex Minimization
An existing general framework for dealing with such objective functions is the online submodular minimization.
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.
LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
For this issue, this study proposes an algorithm whose regret satisfies $O(\log(T))$ in the setting when the suboptimality gap is lower-bounded.
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
Follow-The-Regularized-Leader (FTRL) is known as an effective and versatile approach in online learning, where appropriate choice of the learning rate is crucial for smaller regret.
Fast Rates in Online Convex Optimization by Exploiting the Curvature of Feasible Sets
We first prove that if an optimal decision is on the boundary of a feasible set and the gradient of an underlying loss function is non-zero, then the algorithm achieves a regret upper bound of $O(\rho \log T)$ in stochastic environments.
Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
This development allows us to significantly improve the existing regret bounds of best-of-both-worlds (BOBW) algorithms, which achieves nearly optimal bounds both in stochastic and adversarial environments.
Replicability is Asymptotically Free in Multi-armed Bandits
For the analysis of these algorithms, we propose a principled approach to limiting the probability of nonreplication.
Best-of-Both-Worlds Linear Contextual Bandits
The goal of this study is to develop a strategy that is effective in both stochastic and adversarial environments, with theoretical guarantees.
New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem
Firstly, we show that a mixture distribution that has a greedy-applicable component is also greedy-applicable.
Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
With this result, we establish several algorithms with three types of adaptivity: sparsity, game-dependency, and best-of-both-worlds (BOBW).
Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds
At the higher level, the proposed algorithm adapts to a variety of types of environments.
Best-of-Both-Worlds Algorithms for Partial Monitoring
This study considers the partial monitoring problem with $k$-actions and $d$-outcomes and provides the first best-of-both-worlds algorithms, whose regrets are favorably bounded both in the stochastic and adversarial regimes.
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 $i$.
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: strongly observable graphs yield minimax regret of $\tilde{\Theta}( \alpha^{1/2} T^{1/2} )$, while 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.
Online Task Assignment Problems with Reusable Resources
The key features of our problem are (1) an agent is reusable, i. e., an agent comes back to the market after completing the assigned task, (2) an agent may reject the assigned task to stay the market, and (3) a task may accommodate multiple agents.
Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits
This study aims to develop bandit algorithms that automatically exploit tendencies of certain environments to improve performance, without any prior knowledge regarding the environments.
On Optimal Robustness to Adversarial Corruption in Online Decision Problems
The main contribution of this paper is to show that optimal robustness can be expressed by a square-root dependency on the amount of corruption.
Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions
However, there is a gap of $\tilde{O}(\max(\sqrt{d}, \sqrt{k}))$ between the current best upper and lower bounds, where $d$ is the dimension of the feature vectors, $k$ is the number of the chosen arms in a round, and $\tilde{O}(\cdot)$ ignores the logarithmic factors.
Delay and Cooperation in Nonstochastic Linear Bandits
This paper offers a nearly optimal algorithm for online linear optimization with delayed bandit feedback.
A Tight Lower Bound and Efficient Reduction for Swap Regret
Swap regret, a generic performance measure of online decision-making algorithms, plays an important role in the theory of repeated games, along with a close connection to correlated equilibria in strategic games.
Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits
We propose novel algorithms with first- and second-order regret bounds for adversarial linear bandits.
Submodular Function Minimization with Noisy Evaluation Oracle
This paper considers submodular function minimization with \textit{noisy evaluation oracles} that return the function value of a submodular objective with zero-mean additive noise.
Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback
Our algorithm for non-stochastic settings has an oracle complexity of $\tilde{O}( T )$ and is the first algorithm that achieves both a regret bound of $\tilde{O}( \sqrt{T} )$ and an oracle complexity of $\tilde{O} ( \mathrm{poly} ( T ) )$, given only linear optimization oracles.
Improved Regret Bounds for Bandit Combinatorial Optimization
\textit{Bandit combinatorial optimization} is a bandit framework in which a player chooses an action within a given finite set $\mathcal{A} \subseteq \{ 0, 1 \}^d$ and incurs a loss that is the inner product of the chosen action and an unobservable loss vector in $\mathbb{R} ^ d$ in each round.
An Arm-Wise Randomization Approach to Combinatorial Linear Semi-Bandits
Our empirical evaluation with artificial and real-world datasets demonstrates that the proposed algorithms with the arm-wise randomization technique outperform the existing algorithms without this technique, especially for the clustered case.
Regret Bounds for Online Portfolio Selection with a Cardinality Constraint
Online portfolio selection is a sequential decision-making problem in which a learner repetitively selects a portfolio over a set of assets, aiming to maximize long-term return.
Unbiased Objective Estimation in Predictive Optimization
Predictive optimization, however, suffers from the problem of a calculated optimal solution’s being evaluated too optimistically, i. e., the value of the objective function is overestimated.
Causal Bandits with Propagating Inference
In this setting, the arms are identified with interventions on a given causal graph, and the effect of an intervention propagates throughout all over the causal graph.
Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation
Under these assumptions, we present polynomial-time sublinear-regret algorithms for the online sparse linear regression.
Large-Scale Price Optimization via Network Flow
On the basis of this connection, we propose an efficient algorithm that employs network flow algorithms.
Optimization Beyond Prediction: Prescriptive Price Optimization
This paper addresses a novel data science problem, prescriptive price optimization, which derives the optimal price strategy to maximize future profit/revenue on the basis of massive predictive formulas produced by machine learning.
