mlsanityData to 7 Oct 2026

Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks

arXiv 2404.03099 ↗First posted 3 Apr 2024cs.LG cs.AI cs.CEcited by 10

Not on the map. Why?

Abstract (arXiv)

Operator learning is a rising field of scientific computing where inputs or outputs of a machine learning model are functions defined in infinite-dimensional spaces. In this paper, we introduce NEON (Neural Epistemic Operator Networks), an architecture for generating predictions with uncertainty using a single operator network backbone, which presents orders of magnitude less trainable parameters than deep ensembles of comparable performance. We showcase the utility of this method for sequential decision-making by examining the problem of composite Bayesian Optimization (BO), where we aim to optimize a function f=gcirc h, where h:X→ C(Y,ℝds) is an unknown map which outputs elements of a function space, and g: C(Y,ℝds)→ ℝ is a known and cheap-to-compute functional. By comparing our approach to other state-of-the-art methods on toy and real world scenarios, we demonstrate that NEON achieves state-of-the-art performance while requiring orders of magnitude less trainable parameters.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 27 of its 48 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

27 of 48 references.

References · 27

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  6. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 537
  7. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  8. 2022MIONet: Learning multiple-input operators via tensor productcited by 180
  9. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
  10. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  11. 2023Unexpected Improvements to Expected Improvement for Bayesian Optimizationcited by 144
  12. 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
15 more
  1. 2021Epistemic Neural Networkscited by 120
  2. 2022Learning Operators with Coupled Attentioncited by 88
  3. 2021Improved architectures and training algorithms for deep operator networkscited by 85
  4. 2022NOMAD: Nonlinear Manifold Decoders for Operator Learningcited by 81
  5. 2019A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Taskscited by 62
  6. 2019Bayesian Optimization of Composite Functionscited by 45
  7. 2016Parallel Bayesian Global Optimization of Expensive Functionscited by 43
  8. 2020Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologiescited by 41
  9. 2022Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priorscited by 39
  10. 2021Bayesian Optimization with High-Dimensional Outputscited by 32
  11. 2019BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimizationcited by 28
  12. 2020Optimizing Coverage and Capacity in Cellular Networks using Machine Learningcited by 21
  13. 2021Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structurecited by 15
  14. 2020Interferobot: aligning an optical interferometer by a reinforcement learning agentcited by 12
  15. 2023Joint Composite Latent Space Bayesian Optimizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2025Active operator learning with predictive uncertainty quantification for partial differential equationscited by 12
  2. 2024Deep Learning Alternatives of the Kolmogorov Superposition Theoremcited by 11
  3. 2025SPIEDiff: robust learning of long-time macroscopic dynamics from short-time particle simulations with quantified epistemic uncertaintycited by 2
  4. 2025Thompson Sampling in Function Spaces via Neural Operatorscited by 1
  5. 2026Multimodal Scientific Learning Beyond Diffusions and Flowscited by 1
  6. 2025Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic Actuatorscited by 0
  7. 2025Leveraging AI modelling for FDS with Simvue: monitor and optimise for more sustainable simulationscited by 0
  8. 2026A Mutual Information Lower Bound for Multimodal Regression Active Learningcited by 0
  9. 2026Structure-preserving uncertainty quantification for GENERIC dynamicscited by 0
  10. 2026Sequential operator learning under dependent datacited by 0