2015

Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions

Shah, Amar, Ghahramani, Zoubin

Understand

We develop parallel predictive entropy search (PPES), a novel algorithm for Bayesian optimization of expensive black-box objective functions.

At each iteration, PPES aims to select a batch of points which will maximize the information gain about the global maximizer of the objective.
Well known strategies exist for suggesting a single evaluation point based on previous observations, while far fewer are known for selecting batches of points to evaluate in parallel.
The few batch selection schemes that have been studied all resort to greedy methods to compute an optimal batch.

Built on

Lectures on Fourier Integrals
S. Bochner · 1959
Earlier work this paper cites.
Test Functions for Multimodal Search Techniques
J. Shekel · 1971
Earlier work this paper cites.
A Nonparametric Estimation of the Entropy for Absolutely Continuous Distributions
I. Ahmad and P. E. Lin · 1976
Earlier work this paper cites.
Bayesian Approach to Global Optimization: Theory and Applications
J. Mockus · 1989
Earlier work this paper cites.
Information-Based Objective Functions for Active Data Selection
D. J. MacKay · 1992
Earlier work this paper cites.
Bayesian Learning for Neural Networks
R. M. Neal · 1995
Earlier work this paper cites.
A Nonparametric Approach to Noisy and Costly Optimization
B. S. Anderson, A. W. Moore, and D. Cohn · 2000
Earlier work this paper cites.
A Family of Algorithms for Approximate Bayesian Inference
T. P. Minka · 2001
Earlier work this paper cites.
Traveling salesman should not be greedy:domination analysis of greedy-type heuristics for the TSP
G. Gutin, A. Yeo, and A. Zverovich · 2002
Earlier work this paper cites.
Stochastic Optimization Models in Finance
W. Ziemba & R. Vickson · 2006
Earlier work this paper cites.
Gaussian Processes for Machine Learning
Carl Rasmussen and Chris Williams · 2006
Earlier work this paper cites.
Review of Metamodeling Techniques in Support of Engineering Design Optimization
G. Wang and S. Shan · 2007
Earlier work this paper cites.

Similar

Automatic Gait Optimization with Gaussian Process Regression
D. Lizotte, T. Wang, M. Bowling, and D. Schuurmans · 2007
Cited alongside, same era.
Random Features for Large-Scale Kernel Machines
A. Rahimi and B. Recht · 2007
Cited alongside, same era.
Feedback Control of Dynamic Bipedal Robot Locomotion
E. Westervelt and J. Grizzle · 2007
Cited alongside, same era.
Expectation Propagation for Exponential Families
M. Seeger · 2008
Cited alongside, same era.
Practical Bayesian Optimization
D. Lizotte · 2008
Cited alongside, same era.
In Classical Mechanics with MATLAB Applications
J. E. Hasbun · 2008
Cited alongside, same era.
EP: A Quick Reference
T. Minka · 2008
Cited alongside, same era.
A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Applications to Active User Modeling and Hierarchical Reinforcement Learning
E. Brochu, M. Cora, and N. de Freitas · 2009
Cited alongside, same era.
Optimization of ph and nitrogen for enhanced hydrogen production by synechocystis sp. pcc 6803 via statistical and machine learning methods
E. H. Burrows, W. K. Wong, X. Fern, F.W.R. Chaplen, and R.L. Ely · 2009
Cited alongside, same era.
Batch Bayesian Optimization via Simulation Matching
J. Azimi, A. Fern, and X. Z. Fern · 2010
Cited alongside, same era.
Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
N. Srinivas, A. Krause, S. Kakade, and M. Seeger · 2010
Cited alongside, same era.
The Knowledge-Gradient Algorithm for Sequencing Experiments in Drug Discovery
D. M. Negoescu, P. I. Frazier, and W. B. Powell · 2011
Cited alongside, same era.

Then

Dealing with Asynchronicity in Parallel Gaussian Process Based Optimization
D. Ginsbourger, J. Janusevskis, and R. Le Riche · 2011
Later among the works it cites.
Practical Bayesian Optimization of Machine Learning Algorithms
J. Snoek, H. Larochelle, and R. P. Adams · 2012
Later among the works it cites.
Entropy Search for Information-Efficient Global Optimization
P. Hennig and C. J. Schuler · 2012
Later among the works it cites.
Parallelizing Exploration-Exploitation Tradeoffs with Gaussian Process Bandit Optimization
T. Desautels, A. Krause, and J. Burdick · 2012
Later among the works it cites.
Collaborative Gaussian Processes for Preference Learning
N. Houlsby, J. M. Hernández-Lobato, F. Huszar, and Z. Ghahramani · 2012
Later among the works it cites.
Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Exploration
E. Contal, D. Buffoni, D. Robicquet, and N. Vayatis · 2013
Later among the works it cites.
Gaussian Probabilities and Expectation Propagation
Original
J. P. Cunningham, P. Hennig, and S. Lacoste-Julien · 2013
Later among the works it cites.
UCI Machine Learning Repository, 2013
K. Bache and M. Lichman · 2013
Later among the works it cites.
Student- t t Processes as Alternatives to Gaussian Processes
A. Shah, A. G. Wilson, and Z. Ghahramani · 2014
Later among the works it cites.
Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
J. M. Hernández-Lobato, M. W. Hoffman, and Z. Ghahramani · 2014
Later among the works it cites.
Scalable Bayesian Optimization Using Deep Neural Networks
J. Snoek, O. Rippel, K. Swersky, R. Kiros, N. Satish, N. Sundaram, M. Patwary, Mr Prabat, and R. P. Adams · 2015
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…