Many real-world situations allow for the acquisition of additional relevant information when making an assessment with limited or uncertain data. However, traditional ML approaches either require all features to be acquired beforehand or regard part of them as missing data that cannot be acquired. In this work, we consider models that perform active feature acquisition (AFA) and query the environment for unobserved features to improve the prediction assessments at evaluation time. Our work reformulates the Markov decision process (MDP) that underlies the AFA problem as a generative modeling task and optimizes a policy via a novel model-based approach. We propose learning a generative surrogate model (GSM) that captures the dependencies among input features to assess potential information gain from acquisitions. The GSM is leveraged to provide intermediate rewards and auxiliary information to aid the agent navigate a complicated high-dimensional action space and sparse rewards. Furthermore, we extend AFA in a task we coin active instance recognition (AIR) for the unsupervised case where the target variables are the unobserved features themselves and the goal is to collect information for a particular instance in a cost-efficient way. Empirical results demonstrate that our approach achieves considerably better performance than previous state of the art methods on both supervised and unsupervised tasks.
Hyperparameter optimization (HPO) is generally treated as a bi-level optimization problem that involves fitting a (probabilistic) surrogate model to a set of observed hyperparameter responses, e.g. validation loss, and consequently maximizing an acquisition function using a surrogate model to identify good hyperparameter candidates for evaluation. The choice of a surrogate and/or acquisition function can be further improved via knowledge transfer across related tasks. In this paper, we propose a novel transfer learning approach, defined within the context of model-based reinforcement learning,…
We develop novel methodology for active feature acquisition (AFA), the study of how to sequentially acquire a dynamic (on a per instance basis) subset of features that minimizes acquisition costs whilst still yielding accurate predictions. The AFA framework can be useful in a myriad of domains, including health care applications where the cost of acquiring additional features for a patient (in terms of time, money, risk, etc.) can be weighed against the expected improvement to diagnostic performance. Previous approaches for AFA have employed either: deep learning RL techniques, which have diff…
Department of Computer Science, Aalto University, Finland（芬兰阿尔托大学计算机科学系）；ELLIS Institute Finland（芬兰ELLIS研究所）；Department of Computer Science, University of Manchester, UK（英国曼彻斯特大学计算机科学系）
NTT Communication Science Laboratories（NTT通信科学实验室）
For Bayesian optimization (BO) on high-dimensional data with complex structure, neural network-based kernels for Gaussian processes (GPs) have been used to learn flexible surrogate functions by the high representation power of deep learning. However, existing methods train neural networks by maximizing the marginal likelihood, which do not directly improve the BO performance. In this paper, we propose a meta-learning method for BO with neural network-based kernels that minimizes the expected gap between the true optimum value and the best value found by BO. We model a policy, which takes the c…
Hyperparameter tuning is an omnipresent problem in machine learning as it is an integral aspect of obtaining the state-of-the-art performance for any model. Most often, hyperparameters are optimized just by training a model on a grid of possible hyperparameter values and taking the one that performs best on a validation sample (grid search). More recently, methods have been introduced that build a so-called surrogate model that predicts the validation loss for a specific hyperparameter setting, model and dataset and then sequentially select the next hyperparameter to test, based on a heuristic…
Conditional deep generative models as surrogates for spatial field solution reconstruction with quantified uncertainty in Structural Health Monitoring applications
National Technical University of Athens（雅典国立技术大学）；School of Naval Architecture and Marine Engineering（船舶与海洋工程学院）
The acquisition function, a critical component in Bayesian optimization (BO), can often be written as the expectation of a utility function under a surrogate model. However, to ensure that acquisition functions are tractable to optimize, restrictions must be placed on the surrogate model and utility function. To extend BO to a broader class of models and utilities, we propose likelihood-free BO (LFBO), an approach based on likelihood-free inference. LFBO directly models the acquisition function without having to separately perform inference with a probabilistic surrogate model. We show that co…
Informing Acquisition Functions via Foundation Models for Molecular Discovery
Department of Computer Science, University of Toronto（计算机科学系，多伦多大学）；NVIDIA Research Seattle Robotics Lab (SRL)（NVIDIA研究塞班机器人实验室）；University of Sydney（悉尼大学）；Department of Chemical Engineering & Applied Chemistry, University of Toronto（化学工程与应用化学系，多伦多大学）；Acceleration Consortium（加速联盟）；Data Science Institute（数据科学研究所）；Vector Institute（向量研究所）；Robotics Institute（机器人研究所）；Canadian Institute for Advanced Research (CIFAR)（加拿大高级研究研究院）
FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes
ETSIAE-UPM-School of Aeronautics, Universidad Politécnica de Madrid（马德里理工大学航空学院）；Institute for Cross-Disciplinary Physics and Complex Systems (IFISC, CSIC-UIB)（跨学科物理与复杂系统研究所（IFISC，CSIC-UIB））；Center for Computational Simulation, Universidad Politécnica de Madrid（马德里理工大学计算模拟中心）
NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
University of Macau（澳门大学）；Fudan University（复旦大学）；Renmin University of China（中国人民大学）；Wuhan University（武汉大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Southampton（南安普顿大学）；Hong Kong Baptist University（香港 Baptist大学）
Global optimization problems whose objective function is expensive to evaluate can be solved effectively by recursively fitting a surrogate function to function samples and minimizing an acquisition function to generate new samples. The acquisition step trades off between seeking for a new optimization vector where the surrogate is minimum (exploitation of the surrogate) and looking for regions of the feasible space that have not yet been visited and that may potentially contain better values of the objective function (exploration of the feasible space). This paper proposes a new global optimi…
Imperial College London（帝国理工学院）；SLAC National Accelerator Laboratory（SLAC国家加速器实验室）；University of Oxford（牛津大学）
We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many processes are modeled with non-differentiable simulators with intractable likelihoods. Optimization of these forward models is particularly challenging, especially when the simulator is stochastic. To address such cases, we introduce the use of deep generative models to iteratively approximate the simulator in local neighborhoods of the parameter space. We demonstrate that these local surrogates can be used to approximate…
SURGIN: SURrogate-guided Generative INversion for subsurface multiphase flow with quantified uncertainty
Department of Geotechnical Engineering, College of Civil Engineering, Tongji University（同济大学土木工程学院地质工程系）；Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education, Tongji University（教育部同济大学地质与地下工程重点实验室）；Physical Science and Engineering Division, King Abdullah University of Science and Technology (KAUST)（卡布斯科学与技术大学（KAUST）物理科学与工程系）；State Key Laboratory of Marine Geology, Tongji University（同济大学海洋地质国家重点实验室）；Tencent SSV（腾讯SSV）；Tencent SD（腾讯SD）
Skoltech（斯科尔科沃科技学院）；National Research University Higher School of Economics（俄罗斯国立高等经济研究大学）；IITP RAS（俄罗斯科学院信息传输问题研究所）
The key idea of Bayesian optimization is replacing an expensive target function with a cheap surrogate model. By selection of an acquisition function for Bayesian optimization, we trade off between exploration and exploitation. The acquisition function typically depends on the mean and the variance of the surrogate model at a given point. The most common Gaussian process-based surrogate model assumes that the target with fixed parameters is a realization of a Gaussian process. However, often the target function doesn't satisfy this approximation. Here we consider target functions that come fro…
The data-centric construction of inexpensive surrogates for fine-grained, physical models has been at the forefront of computational physics due to its significant utility in many-query tasks such as uncertainty quantification. Recent efforts have taken advantage of the enabling technologies from the field of machine learning (e.g. deep neural networks) in combination with simulation data. While such strategies have shown promise even in higher-dimensional problems, they generally require large amounts of training data even though the construction of surrogates is by definition a Small Data pr…
Shape-informed cardiac mechanics surrogates in data-scarce regimes via geometric encoding and generative augmentation
MOX Laboratory, Department of Mathematics, Politecnico di Milano（米兰Politecnico大学数学系MOX实验室）；Division 2.2 Process Simulation, Bundesanstalt für Materialforschung und -prüfung (BAM)（材料研究所（BAM）第2.2过程模拟部）；Department of Mathematics, University of Trento（特伦托大学数学系）
We propose Active Surrogate Estimators (ASEs), a new method for label-efficient model evaluation. Evaluating model performance is a challenging and important problem when labels are expensive. ASEs address this active testing problem using a surrogate-based estimation approach that interpolates the errors of points with unknown labels, rather than forming a Monte Carlo estimator. ASEs actively learn the underlying surrogate, and we propose a novel acquisition strategy, XWED, that tailors this learning to the final estimation task. We find that ASEs offer greater label-efficiency than the curre…
Generative Diffusion Surrogates with Analytical Variance Schedule
University of Oxford（牛津大学）；Princeton University（普林斯顿大学）；Max Planck Institute for Security and Privacy（马克斯·普朗克安全与隐私研究所）；University of Cambridge（剑桥大学）；Gonville & Caius College（贡维尔与凯斯学院）
Physics-Informed Geometric Operators to Support Surrogate, Dimension Reduction and Generative Models for Engineering Design
BAR Technologies（BAR科技公司）；Nazarbayev University（纳扎尔巴耶夫大学）；University of Strathclyde（斯特拉斯克莱德大学）；Foundation for Research & Technology Hellas (FORTH)（希腊研究与技术基金会）；Texas A&M University（德克萨斯农工大学）
Adversarial Agents on Topology Optimization: Understanding the Fragility and Robustness of Deep Learning-based and Physics-Based Design Models under Adversarial Perturbation
Generative Bayesian Computation as a Scalable Alternative to Gaussian Process Surrogates
Booth School of Business, University of Chicago（芝加哥大学商学院）；Department of Systems Engineering and Operations Research, George Mason University（乔治·马歇尔大学系统工程与运营管理系）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Siegen（锡根大学）；University of Mannheim（曼海姆大学）
The efficient, automated search for well-performing neural architectures (NAS) has drawn increasing attention in the recent past. Thereby, the predominant research objective is to reduce the necessity of costly evaluations of neural architectures while efficiently exploring large search spaces. To this aim, surrogate models embed architectures in a latent space and predict their performance, while generative models for neural architectures enable optimization-based search within the latent space the generator draws from. Both, surrogate and generative models, have the aim of facilitating query…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning of language about a wide range of real-world objects. We evaluate the efficacy of this learning by predicting the semantics of objects and comparing the performance with neural and non-neural inputs. We show that this generative approach exhibits promising results in language grounding without pre-specifying visual categories under low resource settings. Our …
Center for Machine Learning (ZML)（机器学习中心（ZML））；Institute for Flow in Additively Manufactured Porous Structures (ISAPS)（添加剂制造多孔结构流动研究所（ISAPS））；Heilbronn University of Applied Sciences（海德堡应用科学大学）
Friedrich-Alexander Universität Erlangen-Nürnberg（弗里德里希-亚历山大大学埃尔兰根-纽伦堡分校）；Technical University of Applied Sciences Amberg-Weiden（安贝格-魏登应用技术大学）；Siemens Healthcare GmbH（西门子医疗有限公司）
A Magnetic Resonance Imaging (MRI) exam typically consists of the acquisition of multiple MR pulse sequences, which are required for a reliable diagnosis. Each sequence can be parameterized through multiple acquisition parameters affecting MR image contrast, signal-to-noise ratio, resolution, or scan time. With the rise of generative deep learning models, approaches for the synthesis of MR images are developed to either synthesize additional MR contrasts, generate synthetic data, or augment existing data for AI training. However, current generative approaches for the synthesis of MR images are…
