DeepAI AI Chat
Log In Sign Up

Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret

by   Daniele Calandriello, et al.
Istituto Italiano di Tecnologia
Università di Genova

Gaussian processes (GP) are a popular Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to complex high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions d and iterations t. Given a set of A alternative to choose from, the overall runtime O(t^3A) quickly becomes prohibitive. In this paper, we introduce BKB (budgeted kernelized bandit), a novel approximate GP algorithm for optimization under bandit feedback that achieves near-optimal regret (and hence near-optimal convergence rate) with near-constant per-iteration complexity and no assumption on the input space or covariance of the GP. Combining a kernelized linear bandit algorithm (GP-UCB) with randomized matrix sketching technique (i.e., leverage score sampling), we prove that selecting inducing points based on their posterior variance gives an accurate low-rank approximation of the GP, preserving variance estimates and confidence intervals. As a consequence, BKB does not suffer from variance starvation, an important problem faced by many previous sparse GP approximations. Moreover, we show that our procedure selects at most Õ(d_eff) points, where d_eff is the effective dimension of the explored space, which is typically much smaller than both d and t. This greatly reduces the dimensionality of the problem, thus leading to a O(TAd_eff^2) runtime and O(A d_eff) space complexity.


page 1

page 2

page 3

page 4


Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification

Gaussian processes (GP) are one of the most successful frameworks to mod...

Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domain by Adaptive Discretization

Gaussian process optimization is a successful class of algorithms (e.g. ...

Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times

Computing a Gaussian process (GP) posterior has a computational cost cub...

Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling

There is significant interest in learning and optimizing a complex syste...

Randomized Gaussian Process Upper Confidence Bound with Tight Bayesian Regret Bounds

Gaussian process upper confidence bound (GP-UCB) is a theoretically prom...

Multiple Adaptive Bayesian Linear Regression for Scalable Bayesian Optimization with Warm Start

Bayesian optimization (BO) is a model-based approach for gradient-free b...

Sequential construction and dimension reduction of Gaussian processes under inequality constraints

Accounting for inequality constraints, such as boundedness, monotonicity...