Adversarially robust optimization with Gaussian processes
In this paper, we consider the problem of Gaussian process (GP) optimization with an added
robustness requirement: The returned point may be perturbed by an adversary, and we …
robustness requirement: The returned point may be perturbed by an adversary, and we …
Misspecified gaussian process bandit optimization
I Bogunovic, A Krause - Advances in neural information …, 2021 - proceedings.neurips.cc
We consider the problem of optimizing a black-box function based on noisy bandit feedback.
Kernelized bandit algorithms have shown strong empirical and theoretical performance for …
Kernelized bandit algorithms have shown strong empirical and theoretical performance for …
Control barriers in bayesian learning of system dynamics
V Dhiman, MJ Khojasteh… - … on Automatic Control, 2021 - ieeexplore.ieee.org
This article focuses on learning a model of system dynamics online, while satisfying safety
constraints. Our objective is to avoid offline system identification or hand-specified models …
constraints. Our objective is to avoid offline system identification or hand-specified models …
On the sublinear regret of GP-UCB
J Whitehouse, A Ramdas… - Advances in Neural …, 2023 - proceedings.neurips.cc
In the kernelized bandit problem, a learner aims to sequentially compute the optimum of a
function lying in a reproducing kernel Hilbert space given only noisy evaluations at …
function lying in a reproducing kernel Hilbert space given only noisy evaluations at …
Probabilistic safety constraints for learned high relative degree system dynamics
MJ Khojasteh, V Dhiman… - … for Dynamics and …, 2020 - proceedings.mlr.press
This paper focuses on learning a model of system dynamics online while satisfying safety
constraints. Our motivation is to avoid offline system identification or hand-specified …
constraints. Our motivation is to avoid offline system identification or hand-specified …
Neural contextual bandits without regret
P Kassraie, A Krause - International Conference on Artificial …, 2022 - proceedings.mlr.press
Contextual bandits are a rich model for sequential decision making given side information,
with important applications, eg, in recommender systems. We propose novel algorithms for …
with important applications, eg, in recommender systems. We propose novel algorithms for …
Corruption-tolerant gaussian process bandit optimization
I Bogunovic, A Krause… - … Conference on Artificial …, 2020 - proceedings.mlr.press
We consider the problem of optimizing an unknown (typically non-convex) function with a
bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit …
bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit …
A domain-shrinking based bayesian optimization algorithm with order-optimal regret performance
We consider sequential optimization of an unknown function in a reproducing kernel Hilbert
space. We propose a Gaussian process-based algorithm and establish its order-optimal …
space. We propose a Gaussian process-based algorithm and establish its order-optimal …
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 …
optimization of functions having a bounded norm is some Reproducing Kernel Hilbert Space …
Significance of gradient information in bayesian optimization
We consider the problem of Bayesian Optimization (BO) in which the goal is to design an
adaptive querying strategy to optimize a function $ f:[0, 1]^ d\mapsto\reals $. The function is …
adaptive querying strategy to optimize a function $ f:[0, 1]^ d\mapsto\reals $. The function is …