paper-with-me

Papers

Gaussian Process Surrogate Models for Neural Networks

2022-08-11 · Michael Y. Li, Erin Grant, Thomas L. Griffiths

Not being able to understand and predict the behavior of deep learning systems makes it hard to decide what architecture and algorithm to use for a given problem. In science and engineering, modeling is a methodology used to understand complex systems whose internal processes are opaque. Modeling replaces a complex system with a simpler, more interpretable surrogate. Drawing inspiration from this, we construct a class of surrogate models for neural networks using Gaussian processes. Rather than deriving kernels for infinite neural networks, we learn kernels empirically from the naturalistic behavior of finite neural networks. We demonstrate our approach captures existing phenomena related to the spectral bias of neural networks, and then show that our surrogate models can be used to solve practical problems such as identifying which points most influence the behavior of specific neural networks and predicting which architectures and algorithms will generalize well for specific datasets.

📄 PDF Abstract BibTeX arXiv:2208.06028

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Necessary and Sufficient Conditions for Surrogate Functions of Pareto Frontiers and Their Synthesis Using Gaussian Processes

2015-05-19 · Conrado Silva Miranda, Fernando José Von Zuben

This paper introduces the necessary and sufficient conditions that surrogate functions must satisfy to properly define frontiers of non-dominated solutions in multi-objective optimization problems. These new conditions w…

Gaussian Processesvalid

BITS for GAPS: Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates

2025-11-20 · Kyla D. Jones, Alexander W. Dowling arxiv

We introduce Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS), a framework enabling information-theoretic experimental design of Gaussian process-based surrogate models…

Adaptive Generation-Based Evolution Control for Gaussian Process Surrogate Models

2017-09-29 · Jakub Repicky, Lukas Bajer, Zbynek Pitra, Martin Holena

The interest in accelerating black-box optimizers has resulted in several surrogate model-assisted version of the Covariance Matrix Adaptation Evolution Strategy, a state-of-the-art continuous black-box optimizer. The ve…

Gaussian Processes

Variational Bayesian surrogate modelling with application to robust design optimisation

2024-04-23 · Thomas A. Archbold, Ieva Kazlauskaite, Fehmi Cirak

Surrogate models provide a quick-to-evaluate approximation to complex computational models and are essential for multi-query problems like design optimisation. The inputs of current deterministic computational models are…

Bayesian InferenceDimensionality ReductionRobust Design

Adaptive Gaussian process surrogates for Bayesian inference

2018-09-27 · Timur Takhtaganov, Juliane Müller

We present an adaptive approach to the construction of Gaussian process surrogates for Bayesian inference with expensive-to-evaluate forward models. Our method relies on the fully Bayesian approach to training Gaussian p…

Bayesian Inferenceglobal-optimization