arXiv research

New method tackles online DR-submodular maximization with improved regret guarantees.

In this paper, we propose three online algorithms for submodular maximisation. The first one, Mono-Frank-Wolfe, reduces the number of per-function gradient evaluations from $T^{1/2}$ [Chen2018Online] and $T^{3/2}$ [chen2018projection] to 1, and achieves a $(1-1/e)$-regret bound of $O(T^{4/5})$. The second one, Bandit-F…

Inexact acquisition solutions in BO lead to sublinear cumulative regret.

New algorithm reduces submodular maximization regret to nearly optimal bounds.

New framework analyzes regret in guided diffusion for optimizing structured inputs.

Paper proposes DG-ETC for online submodular maximization with stochastic bandit feedback.

The paper tackles adaptive policy selection to maximize social welfare, achieving optimal regret bounds.

Paper proposes new $γ$-regret measure for non-episodic RL.

New algorithms reduce regret for online submodular maximization under various conditions.

We study combinatorial multi-armed bandit with probabilistically triggered arms (CMAB-T) and semi-bandit feedback. We resolve a serious issue in the prior CMAB-T studies where the regret bounds contain a possibly exponentially large factor of $1/p^*$, where $p^*$ is the minimum positive probability that an arm is trigg…

New framework for online influencer selection considering cost constraints.

Dynamic pricing improves DeFi lending efficiency by reducing regret to logarithmic levels.

Study improves CTS's approximation regret for combinatorial bandits.

New algorithm reduces combinatorial semi-bandit regret efficiently.

Optimizes profit in targeted marketing across multiple markets with varying marketing expenditures.

In this paper, we study fundamental problems of maximizing DR-submodular continuous functions that have real-world applications in the domain of machine learning, economics, operations research and communication systems. It captures a subclass of non-convex optimization that provides both theoretical and practical guar…

The paper optimizes regret using covariance between costs and decisions.

Algorithm maximizes revenue from user choices with contextual information.

Improved algorithm for bandits with delayed feedback, combining adversarial and stochastic performance.

We propose minimum regret search (MRS), a novel acquisition function for Bayesian optimization. MRS bears similarities with information-theoretic approaches such as entropy search (ES). However, while ES aims in each query at maximizing the information gain with respect to the global maximum, MRS aims at minimizing the…

A new mechanism reduces expert belief regret in online forecasting.

New algorithm for multi-player bandits with selfish players, achieving logarithmic regret.

Diminishing-returns (DR) submodular optimization is an important field with many real-world applications in machine learning, economics and communication systems. It captures a subclass of non-convex optimization that provides both practical and theoretical guarantees. In this paper, we study the fundamental problem of…

In this paper, we study the combinatorial multi-armed bandit problem (CMAB) with probabilistically triggered arms (PTAs). Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove that a class of upper confidence bound (UCB) policies, named Combinatorial UCB with exploration …

No-regret learning with strategic experts, incentivized.

Algorithm maximizes user rewards under per-item budget constraints.

We study the online influence maximization problem in social networks under the independent cascade model. Specifically, we aim to learn the set of "best influencers" in a social network online while repeatedly interacting with it. We address the challenges of (i) combinatorial action space, since the number of feasibl…

This paper solves the best arm identification problem with both quick commitment and reward maximization.

Improved regret bounds for online convex optimization under stochastic and adversarial settings.

Proposes a new sampling method for online learning with cumulative oversampling.

We study how the regret guarantees of nonstochastic multi-armed bandits can be improved, if the effective range of the losses in each round is small (e.g. the maximal difference between two losses in a given round). Despite a recent impossibility result, we show how this can be made possible under certain mild addition…

Algorithm improves RL model selection for repeated games with utility maximization.

New algorithm for competing influence spread in unknown networks.

Protocol learns pure quantum states with minimal disturbance.

Maximizing trading volume in online learning framework between traders.

Bayesian optimization tackles expensive discrete and mixed parameter spaces.

Framework for games with uncertain parameters, ensuring no player can improve by changing strategy.

We consider the combinatorial multi-armed bandit (CMAB) problem, where the reward function is nonlinear. In this setting, the agent chooses a batch of arms on each round and receives feedback from each arm of the batch. The reward that the agent aims to maximize is a function of the selected arms and their expectations…

New algorithm for maximizing revenue in multinomial logistic bandits.

Optimal simple regret bound for Gaussian Process bandits.

New insights into balancing reward and fairness in stochastic MAB.

New bounds on IDS for RL show how to balance computation and learning efficiency.

In several realistic situations, an interactive learning agent can practice and refine its strategy before going on to be evaluated. For instance, consider a student preparing for a series of tests. She would typically take a few practice tests to know which areas she needs to improve upon. Based of the scores she obta…

Bayesian quadrature optimization tackles uncertainty in distributional samples.

Study personalizes user experience to maximize rewards with patience budget.

New algorithm reduces dynamic regret in time-varying movement costs.

Paper presents an algorithm for optimal regret in communicating Markov decision processes.

Algorithm maximizes revenue-risk by estimating price impact kernel and optimizing control problems.