paper-with-me

홈 › Papers

Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers

2022-01-30 · Rui P. Cardoso, Emma Hart, David Burth Kurka, Jeremy V. Pitt

Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can be computationally prohibitive. Here we propose a method to overcome this limitation by using a surrogate model which estimates the behavioural distance between two neural network architectures required to calculate the sparseness term in Novelty Search. We demonstrate a speedup of 10 times over previous work and significantly improve on previous reported results on three benchmark datasets from Computer Vision -- CIFAR-10, CIFAR-100, and SVHN. This results from the expanded architecture search space facilitated by using a surrogate. Our method represents an improved paradigm for implementing horizontal scaling of learning algorithms by making an explicit search for diversity considerably more tractable for the same bounded resources.

📄 PDF Abstract BibTeX arXiv:2201.12896

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Towards explainable meta-learning

2020-02-11 · Katarzyna Woźnica, Przemysław Biecek

Meta-learning is a field that aims at discovering how different machine learning algorithms perform on a wide range of predictive tasks. Such knowledge speeds up the hyperparameter tuning or feature engineering. With the…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Feature EngineeringMeta-Learning

Linking intra- and extra-cellular metabolic domains via neural-network surrogates for dynamic metabolic control

2023-10-26 · Sebastián Espinel-Ríos, José L. Avalos

We outline a modeling and optimization strategy for investigating dynamic metabolic engineering interventions. Our framework is particularly useful at the early stages of research and development, often constrained by li…

Guided evolutionary strategies: Augmenting random search with surrogate gradients

2018-06-26 · ICLR 2019 5 · Niru Maheswaranathan, Luke Metz, George Tucker, Dami Choi 외

Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the …

Meta-LearningReinforcement Learning

Active learning of deep surrogates for PDEs: Application to metasurface design

2020-08-24 · Raphaël Pestourie, Youssef Mroueh, Thanh V. Nguyen, Payel Das 외

Surrogate models for partial-differential equations are widely used in the design of meta-materials to rapidly evaluate the behavior of composable components. However, the training cost of accurate surrogates by machine …

Active Learning

NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimization

2026-07-26 · Jintao He, Huixiang Zhen, Wenyin Gong arxiv

Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited. Traditional evolutionary algorithms and Meta-BlackBox Optimization (M…