Neural Model-based Optimization with Right-Censored Observations

by   Katharina Eggensperger, et al.

In many fields of study, we only observe lower bounds on the true response value of some experiments. When fitting a regression model to predict the distribution of the outcomes, we cannot simply drop these right-censored observations, but need to properly model them. In this work, we focus on the concept of censored data in the light of model-based optimization where prematurely terminating evaluations (and thus generating right-censored data) is a key factor for efficiency, e.g., when searching for an algorithm configuration that minimizes runtime of the algorithm at hand. Neural networks (NNs) have been demonstrated to work well at the core of model-based optimization procedures and here we extend them to handle these censored observations. We propose (i) a loss function based on the Tobit model to incorporate censored samples into training and (ii) use an ensemble of networks to model the posterior distribution. To nevertheless be efficient in terms of optimization-overhead, we propose to use Thompson sampling s.t. we only need to train a single NN in each iteration. Our experiments show that our trained regression models achieve a better predictive quality than several baselines and that our approach achieves new state-of-the-art performance for model-based optimization on two optimization problems: minimizing the solution time of a SAT solver and the time-to-accuracy of neural networks.


page 1

page 2

page 3

page 4


Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels

In NeuroEvolution, the topologies of artificial neural networks are opti...

Bayesian Optimization With Censored Response Data

Bayesian optimization (BO) aims to minimize a given blackbox function us...

Initial Design Strategies and their Effects on Sequential Model-Based Optimization

Sequential model-based optimization (SMBO) approaches are algorithms for...

Reliable Offline Model-based Optimization for Industrial Process Control

In the research area of offline model-based optimization, novel and prom...

Model Inversion Networks for Model-Based Optimization

In this work, we aim to solve data-driven optimization problems, where t...

GLISp-r: A preference-based optimization algorithm with convergence guarantees

Preference-based optimization algorithms are iterative procedures that s...

Please sign up or login with your details

Forgot password? Click here to reset