Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information

• URL: http://arxiv.org/abs/2104.09460v1
• Date: Mon, 19 Apr 2021 17:22:11 GMT
• Title: Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
• Authors: Willie Neiswanger, Ke Alexander Wang, Stefano Ermon
• Abstract summary: In many real world problems, we want to infer some property of an expensive black-box function f, given a budget of T function evaluations. We present a procedure, InfoBAX, that sequentially chooses queries that maximize mutual information with respect to the algorithm's output. On these problems, InfoBAX uses up to 500 times fewer queries to f than required by the original algorithm.
• Score: 78.78486761923855
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many real world problems, we want to infer some property of an expensive black-box function f, given a budget of T function evaluations. One example is budget constrained global optimization of f, for which Bayesian optimization is a popular method. Other properties of interest include local optima, level sets, integrals, or graph-structured information induced by f. Often, we can find an algorithm A to compute the desired property, but it may require far more than T queries to execute. Given such an A, and a prior distribution over f, we refer to the problem of inferring the output of A using T evaluations as Bayesian Algorithm Execution (BAX). To tackle this problem, we present a procedure, InfoBAX, that sequentially chooses queries that maximize mutual information with respect to the algorithm's output. Applying this to Dijkstra's algorithm, for instance, we infer shortest paths in synthetic and real-world graphs with black-box edge costs. Using evolution strategies, we yield variants of Bayesian optimization that target local, rather than global, optima. On these problems, InfoBAX uses up to 500 times fewer queries to f than required by the original algorithm. Our method is closely connected to other Bayesian optimal experimental design procedures such as entropy search methods and optimal sensor placement using Gaussian processes.

Related papers

• Practical First-Order Bayesian Optimization Algorithms [0.0]
  We propose a class of practical FOBO algorithms that efficiently utilize the information from the gradient GP to identify potential query points with zero gradients. We validate the performance of our proposed algorithms on several test functions and show that our algorithms outperform state-of-the-art FOBO algorithms.
  arXiv  Detail & Related papers  (2023-06-19T10:05:41Z)
• Experience in Engineering Complex Systems: Active Preference Learning with Multiple Outcomes and Certainty Levels [1.5257326975704795]
  Black-box optimization refers to the problem whose objective function and/or constraint sets are either unknown, inaccessible, or non-existent. The algorithm so-called Active Preference Learning has been developed to exploit this specific information. Our approach aims to extend the algorithm in such a way that can exploit further information effectively.
  arXiv  Detail & Related papers  (2023-02-27T15:55:37Z)
• Generalizing Bayesian Optimization with Decision-theoretic Entropies [102.82152945324381]
  We consider a generalization of Shannon entropy from work in statistical decision theory. We first show that special cases of this entropy lead to popular acquisition functions used in BO procedures. We then show how alternative choices for the loss yield a flexible family of acquisition functions.
  arXiv  Detail & Related papers  (2022-10-04T04:43:58Z)
• Efficient computation of the Knowledge Gradient for Bayesian Optimization [1.0497128347190048]
  One-shot Hybrid KG is a new approach that combines several of the previously proposed ideas and is cheap to compute as well as powerful and efficient. All experiments are implemented in BOTorch and show empirically drastically reduced computational overhead with equal or improved performance.
  arXiv  Detail & Related papers  (2022-09-30T10:39:38Z)
• Ada-BKB: Scalable Gaussian Process Optimization on Continuous Domain by Adaptive Discretization [21.859940486704264]
  An algorithm such as GPUCB has prohibitive computational complexity. A norere algorithm for functions corroborates the real problem of continuous optimization.
  arXiv  Detail & Related papers  (2021-06-16T07:55:45Z)
• Bayesian Optimistic Optimisation with Exponentially Decaying Regret [58.02542541410322]
  The current practical BO algorithms have regret bounds ranging from $mathcalO(fraclogNsqrtN)$ to $mathcal O(e-sqrtN)$, where $N$ is the number of evaluations. This paper explores the possibility of improving the regret bound in the noiseless setting by intertwining concepts from BO and tree-based optimistic optimisation. We propose the BOO algorithm, a first practical approach which can achieve an exponential regret bound with order $mathcal O(N-sqrt
  arXiv  Detail & Related papers  (2021-05-10T13:07:44Z)
• Aligning Partially Overlapping Point Sets: an Inner Approximation Algorithm [80.15123031136564]
  We propose a robust method to align point sets where there is no prior information about the value of the transformation. Our algorithm does not need regularization on transformation, and thus can handle the situation where there is no prior information about the values of the transformations. Experimental results demonstrate the better robustness of the proposed method over state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2020-07-05T15:23:33Z)
• Private Stochastic Convex Optimization: Optimal Rates in Linear Time [74.47681868973598]
  We study the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. has established the optimal bound on the excess population loss achievable given $n$ samples. We describe two new techniques for deriving convex optimization algorithms both achieving the optimal bound on excess loss and using $O(minn, n2/d)$ gradient computations.
  arXiv  Detail & Related papers  (2020-05-10T19:52:03Z)
• Incorporating Expert Prior in Bayesian Optimisation via Space Warping [54.412024556499254]
  In big search spaces the algorithm goes through several low function value regions before reaching the optimum of the function. One approach to subside this cold start phase is to use prior knowledge that can accelerate the optimisation. In this paper, we represent the prior knowledge about the function optimum through a prior distribution. The prior distribution is then used to warp the search space in such a way that space gets expanded around the high probability region of function optimum and shrinks around low probability region of optimum.
  arXiv  Detail & Related papers  (2020-03-27T06:18:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.