Bayesian Optimization in Weakly Specified Search Space

2017 ◽  
Author(s):  
Vu Nguyen ◽  
Sunil Gupta ◽  
Santu Rane ◽  
Cheng Li ◽  
Svetha Venkatesh
Keyword(s):  
Search Space ◽  
Bayesian Optimization

scholarly journals BOKEI: Bayesian Optimization Using Knowledge of Correlated Torsions and Expected Improvement for Conformer Generation​

2019 ◽  
Author(s):  
Lucian Chan ◽  
Geoffrey Hutchison ◽  
Garrett Morris
Keyword(s):  
Random Search ◽  
Search Space ◽  
Empirical Method ◽  
Fixed Number ◽  
Low Energy ◽  
Intramolecular Interactions ◽  
Bayesian Optimization ◽  
Superior Performance ◽  
Expected Improvement ◽  
Wide Range

<div>A key challenge in conformer sampling is to find low-energy conformations with a small number of energy evaluations. We have recently demonstrated Bayesian optimization as an effective method to search for energetically favorable conformations. This approach balances between <i>exploitation</i> and <i>exploration</i>, and lead to superior performance when compared to exhaustive or random search methods. In this work, we extend strategies on proteins and oligopeptides (e.g. Ramachandran plots of secondary structure) to study the correlated torsions in small molecules. We use a bivariate von Mises distribution to capture the correlations, and use it to constrain the search space. We validate the performance of our Bayesian optimization with prior knowledge (BOKEI) on a dataset consisting of 533 diverse small organic molecules, using a force field (MMFF94) and a semi empirical method (GFN2). We compare BOKEI with Bayesian optimization with expected improvement (BOA-EI), and a genetic algorithm (GA), using a fixed number of energy evaluations. In 70(± 2.1)% of the cases examined, BOKEI finds lower energy conformations than global optimization with BOA-EI or GA. More importantly, these patterns find correlated torsions in 10-15% of molecules in larger data sets, 3-8 times more frequently than previous work. We also find that the BOKEI patterns not only describe steric clashes, but also reflect favorable intramolecular interactions, including hydrogen bonds and π-π stacking. Further understanding of the conformational preferences of molecules will help find low energy conformers efficiently for a wide range of computational modeling applications.</div>

scholarly journals Machine-learning-assisted fabrication: Bayesian optimization of laser-induced graphene patterning using in-situ Raman analysis

2020 ◽  
Author(s):  
Hud Wahab ◽  
Vivek Jain ◽  
Alexander Scott Tyrrell ◽  
Michael Alan Seas ◽  
Lars Kotthoff ◽  
...  
Keyword(s):  
Machine Learning ◽  
Irradiation Time ◽  
Electronic Devices ◽  
Parameter Tuning ◽  
Search Space ◽  
Underlying Mechanism ◽  
Single Step ◽  
Bayesian Optimization ◽  
High Quality ◽  
Optimization Search

The control of the physical, chemical, and electronic properties of laser-induced graphene (LIG) is crucial in the fabrication of flexible electronic devices. However, the optimization of LIG production is time-consuming and costly. Here, we demonstrate state-of-the-art automated parameter tuning techniques using Bayesian optimization to advance rapid single-step laser patterning and structuring capabilities with a view to fabricate graphene-based electronic devices. In particular, a large search space of parameters for LIG explored efficiently. As a result, high-quality LIG patterns exhibiting high Raman G/D ratios at least a factor of four larger than those found in the literature were achieved within 50 optimization iterations in which the laser power, irradiation time, pressure and type of gas were optimized. Human-interpretable conclusions may be derived from our machine learning model to aid our understanding of the underlying mechanism for substrate-dependent LIG growth, e.g. high-quality graphene patterns are obtained at low and high gas pressures for quartz and polyimide, respectively. Our Bayesian optimization search method allows for an efficient experimental design that is independent of the experience and skills of individual researchers, while reducing experimental time and cost and accelerating materials research.

scholarly journals BOKEI: Bayesian Optimization Using Knowledge of Correlated Torsions and Expected Improvement for Conformer Generation​

2019 ◽  
Author(s):  
Lucian Chan ◽  
Geoffrey Hutchison ◽  
Garrett Morris
Keyword(s):  
Random Search ◽  
Search Space ◽  
Empirical Method ◽  
Fixed Number ◽  
Low Energy ◽  
Intramolecular Interactions ◽  
Bayesian Optimization ◽  
Superior Performance ◽  
Expected Improvement ◽  
Wide Range

<div>A key challenge in conformer sampling is to find low-energy conformations with a small number of energy evaluations. We have recently demonstrated Bayesian optimization as an effective method to search for energetically favorable conformations. This approach balances between <i>exploitation</i> and <i>exploration</i>, and lead to superior performance when compared to exhaustive or random search methods. In this work, we extend strategies on proteins and oligopeptides (e.g. Ramachandran plots of secondary structure) to study the correlated torsions in small molecules. We use a bivariate von Mises distribution to capture the correlations, and use it to constrain the search space. We validate the performance of our Bayesian optimization with prior knowledge (BOKEI) on a dataset consisting of 533 diverse small organic molecules, using a force field (MMFF94) and a semi empirical method (GFN2). We compare BOKEI with Bayesian optimization with expected improvement (BOA-EI), and a genetic algorithm (GA), using a fixed number of energy evaluations. In 70(± 2.1)% of the cases examined, BOKEI finds lower energy conformations than global optimization with BOA-EI or GA. More importantly, these patterns find correlated torsions in 10-15% of molecules in larger data sets, 3-8 times more frequently than previous work. We also find that the BOKEI patterns not only describe steric clashes, but also reflect favorable intramolecular interactions, including hydrogen bonds and π-π stacking. Further understanding of the conformational preferences of molecules will help find low energy conformers efficiently for a wide range of computational modeling applications.</div>

scholarly journals Filtering Bayesian optimization approach in weakly specified search space

2018 ◽  
Vol 60 (1) ◽  
pp. 385-413 ◽  
Author(s):  
Vu Nguyen ◽  
Sunil Gupta ◽  
Santu Rana ◽  
Cheng Li ◽  
Svetha Venkatesh
Keyword(s):  
Search Space ◽  
Bayesian Optimization ◽  
Optimization Approach

scholarly journals Efficient Hyperparameter Optimization for Physics-based Character Animation

2021 ◽  
Vol 4 (1) ◽  
pp. 1-19
Author(s):  
Zeshi Yang ◽  
Zhiqi Yin
Keyword(s):  
Control Systems ◽  
Task Difficulty ◽  
State Of The Art ◽  
Optimization Methods ◽  
Search Space ◽  
Character Animation ◽  
Bayesian Optimization ◽  
Efficiency Gain ◽  
Hyperparameter Optimization ◽  
Optimization Framework

Physics-based character animation has seen significant advances in recent years with the adoption of Deep Reinforcement Learning (DRL). However, DRL-based learning methods are usually computationally expensive and their performance crucially depends on the choice of hyperparameters. Tuning hyperparameters for these methods often requires repetitive training of control policies, which is even more computationally prohibitive. In this work, we propose a novel Curriculum-based Multi-Fidelity Bayesian Optimization framework (CMFBO) for efficient hyperparameter optimization of DRL-based character control systems. Using curriculum-based task difficulty as fidelity criterion, our method improves searching efficiency by gradually pruning search space through evaluation on easier motor skill tasks. We evaluate our method on two physics-based character control tasks: character morphology optimization and hyperparameter tuning of DeepMimic. Our algorithm significantly outperforms state-of-the-art hyperparameter optimization methods applicable for physics-based character animation. In particular, we show that hyperparameters optimized through our algorithm result in at least 5x efficiency gain comparing to author-released settings in DeepMimic.

Bayesian optimization of peripheral intraneural stimulation protocols to evoke distal limb movements

2021 ◽  
Author(s):  
Elena Losanno ◽  
Marion Badi ◽  
Sophie Wurth ◽  
Simon Borgognon ◽  
Gregoire Courtine ◽  
...  
Keyword(s):  
Search Space ◽  
Bayesian Optimization ◽  
Objective Functions ◽  
Limb Movements ◽  
Distal Limb ◽  
Motor Functions ◽  
Manual Search ◽  
Online Test ◽  
Stimulation Parameters ◽  
Peripheral Motor

Abstract Objective. Motor neuroprostheses require the identification of stimulation protocols that effectively produce desired movements. Manual search for these protocols can be very time-consuming and often leads to suboptimal solutions, as several stimulation parameters must be personalized for each subject for a variety of target movements. Here, we present an algorithm that efficiently tunes peripheral intraneural stimulation protocols to elicit functionally relevant distal limb movements. Approach. We developed the algorithm using Bayesian Optimization and defined multi-objective functions based on the coordinated recruitment of multiple muscles. We implemented different multi-output Gaussian Processes to model our system and compared their functioning by applying the algorithm offline to data acquired in rats for walking control and in monkeys for hand grasping control. We then performed a preliminary online test in a monkey to experimentally validate the functionality of our method. Main results. Offline, optimal intraneural stimulation protocols for various target motor functions were rapidly identified in both experimental scenarios. Using the model that performed best, the algorithm converged to stimuli that evoked functionally consistent movements with an average number of actions equal to 20% (13% unique) and 20% (16% unique) of the search space size in rats and monkeys, respectively. Online, the algorithm quickly guided the observations to stimuli that elicited functional hand gestures, although more selective motor outputs could have been achieved by refining the objective function used. Significance. These results demonstrate that Bayesian Optimization can reliably and efficiently automate the tuning of peripheral neurostimulation protocols, establishing a translational framework to configure peripheral motor neuroprostheses in clinical applications. The proposed method can potentially be applied to optimize motor functions using other stimulation modalities.

scholarly journals Sequential model based optimization of partially defined functions under unknown constraints

2019 ◽  
Author(s):  
Candelieri Antonio
Keyword(s):  
Optimal Solution ◽  
Search Space ◽  
Bayesian Optimization ◽  
Feasible Region ◽  
Support Vector ◽  
Second Phase ◽  
Test Functions ◽  
Current Estimate ◽  
Sequential Model ◽  
Model Based

AbstractThis paper presents a sequential model based optimization framework for optimizing a black-box, multi-extremal and expensive objective function, which is also partially defined, that is it is undefined outside the feasible region. Furthermore, the constraints defining the feasible region within the search space are unknown. The approach proposed in this paper, namely SVM-CBO, is organized in two consecutive phases, the first uses a Support Vector Machine classifier to approximate the boundary of the unknown feasible region, the second uses Bayesian Optimization to find a globally optimal solution within the feasible region. In the first phase the next point to evaluate is chosen by dealing with the trade-off between improving the current estimate of the feasible region and discovering possible disconnected feasible sub-regions. In the second phase, the next point to evaluate is selected as the minimizer of the Lower Confidence Bound acquisition function but constrained to the current estimate of the feasible region. The main of the paper is a comparison with a Bayesian Optimization process which uses a fixed penalty value for infeasible function evaluations, under a limited budget (i.e., maximum number of function evaluations). Results are related to five 2D test functions from literature and 80 test functions, with increasing dimensionality and complexity, generated through the Emmental-type GKLS software. SVM-CBO proved to be significantly more effective as well as computationally efficient.

scholarly journals Trading Convergence Rate with Computational Budget in High Dimensional Bayesian Optimization

2020 ◽  
Vol 34 (03) ◽  
pp. 2425-2432
Author(s):  
Hung Tran-The ◽  
Sunil Gupta ◽  
Santu Rana ◽  
Svetha Venkatesh
Keyword(s):  
Convergence Rate ◽  
Search Space ◽  
Bayesian Optimization ◽  
Dimensional Structure ◽  
High Dimensional ◽  
Search Spaces ◽  
Novel Approach ◽  
Research Problems ◽  
Computational Budget ◽  
Low Dimensional

Scaling Bayesian optimisation (BO) to high-dimensional search spaces is a active and open research problems particularly when no assumptions are made on function structure. The main reason is that at each iteration, BO requires to find global maximisation of acquisition function, which itself is a non-convex optimization problem in the original search space. With growing dimensions, the computational budget for this maximisation gets increasingly short leading to inaccurate solution of the maximisation. This inaccuracy adversely affects both the convergence and the efficiency of BO. We propose a novel approach where the acquisition function only requires maximisation on a discrete set of low dimensional subspaces embedded in the original high-dimensional search space. Our method is free of any low dimensional structure assumption on the function unlike many recent high-dimensional BO methods. Optimising acquisition function in low dimensional subspaces allows our method to obtain accurate solutions within limited computational budget. We show that in spite of this convenience, our algorithm remains convergent. In particular, cumulative regret of our algorithm only grows sub-linearly with the number of iterations. More importantly, as evident from our regret bounds, our algorithm provides a way to trade the convergence rate with the number of subspaces used in the optimisation. Finally, when the number of subspaces is "sufficiently large", our algorithm's cumulative regret is at most O*(√TγT) as opposed to O*(√DTγT) for the GP-UCB of Srinivas et al. (2012), reducing a crucial factor √D where D being the dimensional number of input space. We perform empirical experiments to evaluate our method extensively, showing that its sample efficiency is better than the existing methods for many optimisation problems involving dimensions up to 5000.

scholarly journals Automated Machine Learning with Monte-Carlo Tree Search

2019 ◽  
Author(s):  
Herilalaina Rakotoarison ◽  
Marc Schoenauer ◽  
Michèle Sebag
Keyword(s):  
Machine Learning ◽  
Monte Carlo ◽  
Search Algorithm ◽  
Search Space ◽  
Bayesian Optimization ◽  
Peak Performance ◽  
Tree Search ◽  
Algorithm Selection ◽  
Monte Carlo Tree Search ◽  
Warm Start

The AutoML approach aims to deliver peak performance from a machine learning  portfolio on the dataset at hand. A Monte-Carlo Tree Search Algorithm Selection and Configuration (Mosaic) approach is presented to tackle this mixed (combinatorial and continuous) expensive optimization problem on the structured search space of ML pipelines. Extensive lesion studies are conducted to independently assess and compare: i) the optimization processes based on Bayesian Optimization or Monte Carlo Tree Search (MCTS); ii) its warm-start initialization based on meta-features or random runs; iii) the ensembling of the solutions gathered along the search. Mosaic is assessed on the OpenML 100 benchmark and the Scikit-learn portfolio, with statistically significant gains over AutoSkLearn, winner of all former AutoML challenges.

Bayesian Optimization Algorithm Applied to Uncertainty Quantification

SPE Journal ◽  
2012 ◽  
Vol 17 (03) ◽  
pp. 865-873 ◽  
Author(s):  
Asaad Abdollahzadeh ◽  
Alan Reynolds ◽  
Mike Christie ◽  
David Corne ◽  
Brian Davies ◽  
...  
Keyword(s):  
Uncertainty Quantification ◽  
Optimization Algorithm ◽  
History Matching ◽  
Search Space ◽  
Population Based ◽  
Optimization Techniques ◽  
Bayesian Optimization ◽  
Similar Response ◽  
Bayesian Optimization Algorithm ◽  
Reservoir Models

Summary Prudent decision making in subsurface assets requires reservoir uncertainty quantification. In a typical uncertainty-quantification study, reservoir models must be updated using the observed response from the reservoir by a process known as history matching. This involves solving an inverse problem, finding reservoir models that produce, under simulation, a similar response to that of the real reservoir. However, this requires multiple expensive multiphase-flow simulations. Thus, uncertainty-quantification studies employ optimization techniques to find acceptable models to be used in prediction. Different optimization algorithms and search strategies are presented in the literature, but they are generally unsatisfactory because of slow convergence to the optimal regions of the global search space, and, more importantly, failure in finding multiple acceptable reservoir models. In this context, a new approach is offered by estimation-of-distribution algorithms (EDAs). EDAs are population-based algorithms that use models to estimate the probability distribution of promising solutions and then generate new candidate solutions. This paper explores the application of EDAs, including univariate and multivariate models. We discuss two histogram-based univariate models and one multivariate model, the Bayesian optimization algorithm (BOA), which employs Bayesian networks for modeling. By considering possible interactions between variables and exploiting explicitly stored knowledge of such interactions, EDAs can accelerate the search process while preserving search diversity. Unlike most existing approaches applied to uncertainty quantification, the Bayesian network allows the BOA to build solutions using flexible rules learned from the models obtained, rather than fixed rules, leading to better solutions and improved convergence. The BOA is naturally suited to finding good solutions in complex high-dimensional spaces, such as those typical in reservoir-uncertainty quantification. We demonstrate the effectiveness of EDA by applying the well-known synthetic PUNQ-S3 case with multiple wells. This allows us to verify the methodology in a well-controlled case. Results show better estimation of uncertainty when compared with some other traditional population-based algorithms.

Sign in / Sign up

Export Citation Format

Share Document