Gaussian process bandit optimization with few batches

Z Li, J Scarlett - International Conference on Artificial …, 2022 - proceedings.mlr.press
In this paper, we consider the problem of black-box optimization using Gaussian Process
(GP) bandit optimization with a small number of batches. Assuming the unknown function …

Optimal order simple regret for Gaussian process bandits

S Vakili, N Bouziani, S Jalali… - Advances in Neural …, 2021 - proceedings.neurips.cc
Consider the sequential optimization of a continuous, possibly non-convex, and expensive
to evaluate objective function $ f $. The problem can be cast as a Gaussian Process (GP) …

On lower bounds for standard and robust gaussian process bandit optimization

X Cai, J Scarlett - International Conference on Machine …, 2021 - proceedings.mlr.press
In this paper, we consider algorithm independent lower bounds for the problem of black-box
optimization of functions having a bounded norm is some Reproducing Kernel Hilbert Space …

Open problem: Tight online confidence intervals for RKHS elements

S Vakili, J Scarlett, T Javidi - Conference on Learning Theory, 2021 - proceedings.mlr.press
Confidence intervals are a crucial building block in the analysis of various online learning
problems. The analysis of kernel-based bandit and reinforcement learning problems utilize …

Multi-scale zero-order optimization of smooth functions in an RKHS

M Lee, S Shekhar, T Javidi - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Consider the problem of optimizing a black-box function under the assumption that the
function is Holder smooth and has bounded norm in the reproducing kernel Hilbert space …

No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints

A Losalka, J Scarlett - International Conference on Artificial …, 2024 - proceedings.mlr.press
We consider the problem of sequentially maximizing an unknown function $ f $ over a set of
actions of the form $(s, x) $, where the selected actions must satisfy a safety constraint with …

Ada-bkb: Scalable gaussian process optimization on continuous domains by adaptive discretization

M Rando, L Carratino, S Villa… - … Conference on Artificial …, 2022 - proceedings.mlr.press
Gaussian process optimization is a successful class of algorithms (eg GP-UCB) to optimize a
black-box function through sequential evaluations. However, for functions with continuous …

Adaptation to Misspecified Kernel Regularity in Kernelised Bandits

Y Liu, A Singh - International Conference on Artificial …, 2023 - proceedings.mlr.press
In continuum-armed bandit problems where the underlying function resides in a reproducing
kernel Hilbert space (RKHS), namely, the kernelised bandit problems, an important open …

Lenient regret and good-action identification in Gaussian process bandits

X Cai, S Gomes, J Scarlett - International Conference on …, 2021 - proceedings.mlr.press
In this paper, we study the problem of Gaussian process (GP) bandits under relaxed
optimization criteria stating that any function value above a certain threshold is “good …

Instance dependent regret analysis of kernelized bandits

S Shekhar, T Javidi - International Conference on Machine …, 2022 - proceedings.mlr.press
We study the problem of designing an adaptive strategy for querying a noisy zeroth-order-
oracle to efficiently learn about the optimizer of an unknown function $ f $. To make the …