mlsanityData to 7 Oct 2026

Generative Adversarial Model-Based Optimization via Source Critic Regularization

arXiv 2402.06532 ↗First posted 9 Feb 2024cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Offline model-based optimization seeks to optimize against a learned surrogate model without querying the true oracle objective function during optimization. Such tasks are commonly encountered in protein design, robotics, and clinical medicine where evaluating the oracle function is prohibitively expensive. However, inaccurate surrogate model predictions are frequently encountered along offline optimization trajectories. To address this limitation, we propose generative adversarial model-based optimization using adaptive source critic regularization (aSCR) -- a task- and optimizer- agnostic framework for constraining the optimization trajectory to regions of the design space where the surrogate function is reliable. We propose a computationally tractable algorithm to dynamically adjust the strength of this constraint, and show how leveraging aSCR with standard Bayesian optimization outperforms existing methods on a suite of offline generative design tasks. Our code is available at https://github.com/michael-s-yao/gabo

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 60 references that are in the map. First posted on arXiv 9 Feb 2024.

Builds on

32 of 60 references.

References · 32

  1. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  2. 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 359
  3. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  4. 2019Evaluating Protein Transfer Learning with TAPEcited by 229
  5. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 199
  6. 2021High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspacescited by 139
  7. 2020Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retrainingcited by 121
  8. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 116
  9. 2019Conditioning by adaptive sampling for robust designcited by 110
  10. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 96
  11. 2019A Survey of Optimization Methods from a Machine Learning Perspectivecited by 90
  12. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 87
20 more
  1. 2024Vanilla Bayesian Optimization Performs Great in High Dimensionscited by 87
  2. 2022Local Latent Space Bayesian Optimization over Structured Inputscited by 78
  3. 2023Diffusion Models for Black-Box Optimizationcited by 75
  4. 2019ROBEL: Robotics Benchmarks for Learning with Low-Cost Robotscited by 70
  5. 2021Keeping it Simple: Language Models can learn Complex Molecular Distributionscited by 68
  6. 2019Bayesian Optimization of Composite Functionscited by 45
  7. 2021Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spacescited by 45
  8. 2021RoMA: Robust Model Adaptation for Offline Model-based Optimizationcited by 39
  9. 2020A Deep Generative Model for Molecule Optimization via One Fragment Modificationcited by 36
  10. 2022Generative Pretraining for Black-Box Optimizationcited by 36
  11. 2022Bidirectional Learning for Offline Infinite-width Model-based Optimizationcited by 35
  12. 2020Population-Based Black-Box Optimization for Biological Sequence Designcited by 29
  13. 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequencescited by 23
  14. 2023ExPT: Synthetic Pretraining for Few-Shot Experimental Designcited by 22
  15. 2021Dynamic Causal Bayesian Optimizationcited by 17
  16. 2019Learning Interpretable Models with Causal Guaranteescited by 11
  17. 2021Multitask Learning and Bandits via Robust Statisticscited by 11
  18. 2023Optimal Transport-Guided Conditional Score-Based Diffusion Modelscited by 11
  19. 2018Bayesian Optimization for Dynamic Problemscited by 10
  20. 2023ROMO: Retrieval-enhanced Offline Model-based Optimizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 4.

10 papers.

  1. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 14
  2. 2024Offline Model-Based Optimization by Learning to Rankcited by 13
  3. 2024Design Editing for Offline Model-based Optimizationcited by 10
  4. 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 6
  5. 2025ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridgecited by 4
  6. 2025Learning Design-Score Manifold to Guide Diffusion Models for Offline Optimizationcited by 1
  7. 2026Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimizationcited by 1
  8. 2026Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Taskscited by 0
  9. 2026Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgetscited by 0
  10. 2026Rethinking Learnability in Offline Data-driven Optimizationcited by 0