Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization

Belakaria, Syrine; Deshwal, Aryan; Jayakodi, Nitthilan Kannappan; Doppa, Janardhan Rao

doi:10.1609/aaai.v34i06.6561

Cited by 52 publications

(60 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common drawback of this family of algorithms is that reduction to single-objective optimization can potentially lead to more exploitation behavior resulting in sub-optimal solutions. PAL (Zuluaga, Sergent, Krause, & Püschel, 2013), PESMO (Hernández-Lobato et al, 2016), and the concurrent works USeMO (Belakaria, Deshwal, Jayakodi, & Doppa, 2020b) and MESMO (Belakaria et al, 2019) are principled algorithms based on information theory. PAL tries to classify the input points based on the learned models into three categories: Pareto optimal, non-Pareto optimal, and uncertain.…”

Section: Single-fidelity Multi-objective Optimizationmentioning

confidence: 99%

Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

Belakaria

Deshwal

Doppa

2021

jair

Self Cite

View full text Add to dashboard Cite

We consider the problem of black-box multi-objective optimization (MOO) using expensive function evaluations (also referred to as experiments), where the goal is to approximate the true Pareto set of solutions by minimizing the total resource cost of experiments. For example, in hardware design optimization, we need to find the designs that trade-off performance, energy, and area overhead using expensive computational simulations. The key challenge is to select the sequence of experiments to uncover high-quality solutions using minimal resources. In this paper, we propose a general framework for solving MOO problems based on the principle of output space entropy (OSE) search: select the experiment that maximizes the information gained per unit resource cost about the true Pareto front. We appropriately instantiate the principle of OSE search to derive efficient algorithms for the following four MOO problem settings: 1) The most basic single-fidelity setting, where experiments are expensive and accurate; 2) Handling black-box constraints which cannot be evaluated without performing experiments; 3) The discrete multi-fidelity setting, where experiments can vary in the amount of resources consumed and their evaluation accuracy; and 4) The continuous-fidelity setting, where continuous function approximations result in a huge space of experiments. Experiments on diverse synthetic and real-world benchmarks show that our OSE search based algorithms improve over state-of-the-art methods in terms of both computational-efficiency and accuracy of MOO solutions.

show abstract

Section: Single-fidelity Multi-objective Optimizationmentioning

confidence: 99%

Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

Belakaria

Deshwal

Doppa

2021

jair

Self Cite

View full text Add to dashboard Cite

show abstract

“…This paper takes the first step to synergistically combine the advantages of latent space and generic/domain-specific kernels to automate the overall BO workflow, which is highly advantageous for scientists and engineers who are the real-users of this technology. We do not claim that LADDER is the optimal algorithm to achieve this goal, but our hope is that LADDER will inspire the BO community to explore this important research direction to develop better algorithms in the future 5 .…”

Section: Discussion and Limitationsmentioning

confidence: 99%

“…For example, in drug design application, each candidate structure is a molecule and evaluation involves performing an expensive physical lab experiment. Bayesian optimization (BO) [59,20] is an effective framework for optimizing expensive black-box functions and has shown great success in practice [63,74,21,6,5]. The key idea is to learn a cheap-to-evaluate surrogate statistical model, e.g., Gaussian process (GP), from past function evaluations and employ it to select inputs with high-utility for evaluation.…”

Section: Introductionmentioning

confidence: 99%

Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces

Deshwal¹,

Doppa²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We consider the problem of optimizing combinatorial spaces (e.g., sequences, trees, and graphs) using expensive black-box function evaluations. For example, optimizing molecules for drug design using physical lab experiments. Bayesian optimization (BO) is an efficient framework for solving such problems by intelligently selecting the inputs with high utility guided by a learned surrogate model. A recent BO approach for combinatorial spaces is through a reduction to BO over continuous spaces by learning a latent representation of structures using deep generative models (DGMs). The selected input from the continuous space is decoded into a discrete structure for performing function evaluation. However, the surrogate model over the latent space only uses the information learned by the DGM, which may not have the desired inductive bias to approximate the target black-box function.To overcome this drawback, this paper proposes a principled approach referred as LADDER. The key idea is to define a novel structure-coupled kernel that explicitly integrates the structural information from decoded structures with the learned latent space representation for better surrogate modeling. Our experiments on real-world benchmarks show that LADDER significantly improves over the BO over latent space method, and performs better or similar to state-of-the-art methods.35th Conference on Neural Information Processing Systems (NeurIPS 2021).

show abstract

“…Uncertainty reduction methods like PAL (Zuluaga et al 2013), PESMO (Hernández-Lobato et al 2016) and the concurrent works USeMO (Belakaria et al 2020) and MESMO (Belakaria, Deshwal, and Doppa 2019) are principled algorithms based on information theory. In each iteration, PAL selects the candidate input for evaluation towards the goal of minimizing the size of uncertain set.…”

Section: Related Workmentioning

confidence: 99%

“…We would like to apologize for the omission of the citation of Takeno et al (2019) under subsection "Approximation 2" in Section 4.2 in Belakaria et al (2020).…”

mentioning

confidence: 99%

Multi-Fidelity Multi-Objective Bayesian Optimization: An Output Space Entropy Search Approach

Belakaria

Deshwal

Doppa

2020

AAAI

Self Cite

View full text Add to dashboard Cite

We study the novel problem of blackbox optimization of multiple objectives via multi-fidelity function evaluations that vary in the amount of resources consumed and their accuracy. The overall goal is to appromixate the true Pareto set of solutions by minimizing the resources consumed for function evaluations. For example, in power system design optimization, we need to find designs that trade-off cost, size, efficiency, and thermal tolerance using multi-fidelity simulators for design evaluations. In this paper, we propose a novel approach referred as Multi-Fidelity Output Space Entropy Search for Multi-objective Optimization (MF-OSEMO) to solve this problem. The key idea is to select the sequence of candidate input and fidelity-vector pairs that maximize the information gained about the true Pareto front per unit resource cost. Our experiments on several synthetic and real-world benchmark problems show that MF-OSEMO, with both approximations, significantly improves over the state-of-the-art single-fidelity algorithms for multi-objective optimization.

show abstract

Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization

Cited by 52 publications

References 11 publications

Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces

Multi-Fidelity Multi-Objective Bayesian Optimization: An Output Space Entropy Search Approach

Contact Info

Product

Resources

About