Bayesian Optimization with Inequality Constraints

By Jacob V. Gardner, Matt J. Kusner, Zhixiang Eddie Xu, Kilian Q. Weinberger, John P. Cunningham. 2014

597 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016, background): “A variant of wEI was proposed in [52] to deal with the case where the function is constrained to be less than some”
Google Vizier: A Service for Black-Box Optimization (2017, background): “In the case of Bayesian Optimization, previous work either assigns them a particularly bad objective value, attempts to incorporate a probability of infeasibility into the acquisition function to penalize points that are likely to be infeasible [3], or tries to explicitly model the shape of the infe”
BoTorch: Programmable Bayesian Optimization in PyTorch (2019, background): “If a is differentiable with respect to ζ , then In B O T ORCH , these chains of derivatives are handled by auto-differentiation.”
A Tutorial on Bayesian Optimization (2018, background): “This was proposed in Section 4 of Schonlau et al. (1998) and studied independently by Gardner et al. (2014).”
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization (2020, methodology): “Importantly, the sequential greedy approach allows for using different random scalarization weights for selecting each of the q candidates. q P AR EGO is extended to the constrained setting by weighting the EI by the probability of feasibility [24].”
CherryPick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics (2017, methodology): “Then, as suggested in [18], we modify the EI acquisition function as: Stopping condition We deﬁne the stopping condition in CherryPick as follows: when the expected improvement in Eqn.”
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization (2016, background): “…thatthe parallel knowledge gradient method finds global optima significantly faster than previous batch Bayesian optimization algorithms on both synthetic test functions and when tuning hyperparameters of practical machine learning algorithms, especially when function evaluations are noisy.”
Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning (2019, methodology): “They would require resorting to constrained BO modelling [16, 13, 14], e.g., to optimize the acquisition function over the ellipsoid, which would add signiﬁcant complexity to the procedure.”
Constraint-Aware Deep Neural Network Compression (2018, methodology): “For a more comprehensive treatment of Gaussian processes and Bayesian optimization, we refer the interested reader to [27, 29, 31].”
CLIP-Q: Deep Network Compression Learning by In-parallel Pruning-Quantization (2018, methodology): “We implemented CLIP-Q in Caffe and used the public Bayesian optimization libraries of [12, 40]”
Learning manipulation skills from a single demonstration (2018, methodology): “There exist different methods of including additional constraints in Bayesian optimization (Gardner et al., 2014; Gelbart et al., 2014; Gramacy and Lee, 2011; Schonlau et al., 1998).”
Constrained Efficient Global Optimization of Expensive Black-box Functions (2022, methodology): “Along this line of research, a group of popular methods (Gardner et al., 2014; Gelbart et al., 2014) encodes the constraint information into the acquisition function (e.g., Constrained Expected Improvement).”
Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020 (2021, background): “Additionally, while we only focused on unconstrained single-objective optimization performance, many relevant problems have additional black-box constraints that need to be satisﬁed or are more naturally phrased as multi-objective optimization problems [12, 13, 21, 32, 40].”
Predictive Entropy Search for Bayesian Optimization with Unknown Constraints (2015, methodology): “…proposed by Schonlau et al. (1998), one method of extending EI to the constrained setting considers the expected feasible improvement, where the constraints are given as above; such approaches have recently been independently developed in Gelbart et al. (2014); Gardner et al. (2014); Snoek (2013).”
Constrained Bayesian Optimization with Noisy Experiments (2017, background): “The third problem is a constrained Branin problem used by Gelbart et al. (2014) and the fourth is a problem given by Gardner et al. (2014); these both have two parameters and one constraint.”