arXiv research

New algorithm optimizes best arm identification with minimal regret.

New meta-learning framework for minimizing simple regret in bandits.

Bayes optimal algorithm under certain conditions doesn't achieve exponential simple regret.

qEUBO optimizes decision-making with noisy feedback.

Distributed Thompson sampling improves regret convergence in constrained communication networks.

Paper analyzes GP-EI for Bayesian optimization with no regret and provides guidance on choosing incumbents.

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…

We prove a new minimax theorem connecting the worst-case Bayesian regret and minimax regret under partial monitoring with no assumptions on the space of signals or decisions of the adversary. We then generalise the information-theoretic tools of Russo and Van Roy (2016) for proving Bayesian regret bounds and combine th…

Bayesian framework learns latent preference archetypes for many-objective optimization.

Bayesian optimization method for permutations accelerates combinatorial search.

New geometric metrics improve Bayesian optimization performance evaluation.

New algorithm learns LQR with $O(\sqrt{T})$ regret using Langevin dynamics and excitation.

Proposes a new PBO method with theoretical guarantees.

DPP-BBO diversifies batched Bayesian optimization using DPPs.

New bounds for Bayesian bandits show prior improves performance.

We develop a new theoretical framework, the \emph{envelope complexity}, to analyze the minimax regret with logarithmic loss functions and derive a Bayesian predictor that adaptively achieves the minimax regret over high-dimensional $\ell_1$-balls within a factor of two. The prior is newly derived for achieving the mini…

How can we efficiently gather information to optimize an unknown function, when presented with multiple, mutually dependent information sources with different costs? For example, when optimizing a robotic system, intelligently trading off computer simulations and real robot testings can lead to significant savings. Exi…

UCB exploration improves best arm identification in fixed-budget settings.

In this paper, we consider the problem of sequentially optimizing a black-box function $f$ based on noisy samples and bandit feedback. We assume that $f$ is smooth in the sense of having a bounded norm in some reproducing kernel Hilbert space (RKHS), yielding a commonly-considered non-Bayesian form of Gaussian process …

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…

New algorithm minimizes Bayesian regret in offline linear bandits.

Novel method for efficient optimization of noisy, expensive hybrid models.

IDS improves sparse linear bandits by balancing information and regret.

Paper improves regret bounds for Gaussian process upper confidence bound in Bayesian optimization.

Improved Thompson Sampling reduces regret in contextual bandits and reinforcement learning.

Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.

Mirror descent linked to information ratio via Bayesian regret bounds.

This paper analyzes regret bounds for Gaussian process Thompson sampling.

New algorithms minimize simple and cumulative regret in contextual bandits.

EBUCB framework achieves optimal regret with bounded approximate inference error.

Bayesian optimisation has gained great popularity as a tool for optimising the parameters of machine learning algorithms and models. Somewhat ironically, setting up the hyper-parameters of Bayesian optimisation methods is notoriously hard. While reasonable practical solutions have been advanced, they can often fail to …

Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.

Posterior sampling-based EI achieves sublinear regret bounds for expensive function optimization.

TVBO optimizes time-varying functions with asymptotically vanishing regret.

New method reduces GP bandit complexity while maintaining good performance.

We consider the problem of Bayesian optimization of a one-dimensional Brownian motion in which the $T$ adaptively chosen observations are corrupted by Gaussian noise. We show that as the smallest possible expected cumulative regret and the smallest possible expected simple regret scale as $Ω(σ\sqrt{T / \log (T)}) \cap …

Paper tackles non-stationary kernelized bandits with near-optimal algorithm.

Bayesian algorithms minimize cumulative regret in decentralized multi-agent bandits.

Enhances RL with function approximation, improving regret bounds.

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…

TS-RSR improves batch Bayesian Optimization by minimizing redundancy and focusing on high uncertainty points.

Bayesian framework reduces online optimization regret.

This paper improves Bayesian optimization methods with tighter regret bounds and practical solutions.

Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better empirical performance compared to the state of the art methods. In this paper, we …

Paper improves Bayesian regret bounds for Thompson Sampling in reinforcement learning.

New algorithm reduces regret in sequential decision-making problems.

In this paper, the problem of maximizing a black-box function $f:\mathcal{X} \to \mathbb{R}$ is studied in the Bayesian framework with a Gaussian Process (GP) prior. In particular, a new algorithm for this problem is proposed, and high probability bounds on its simple and cumulative regret are established. The query po…

Unified CS for GLMs improves bandit regret bounds.