mlsanityData to 14 Oct 2026

ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge

arXiv 2509.16300 ↗First posted 19 Sep 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achieved via learning and optimizing a surrogate function with that offline data. Alternatively, it can also be framed as an inverse modeling task that maps a desired performance to potential input candidates that achieve it. Both approaches are constrained by the limited amount of offline data. To mitigate this limitation, we introduce a new perspective that casts offline optimization as a distributional translation task. This is formulated as learning a probabilistic bridge transforming an implicit distribution of low-value inputs (i.e., offline data) into another distribution of high-value inputs (i.e., solution candidates). Such probabilistic bridge can be learned using low- and high-value inputs sampled from synthetic functions that resemble the target function. These synthetic functions are constructed as the mean posterior of multiple Gaussian processes fitted with different parameterizations on the offline data, alleviating the data bottleneck. The proposed approach is evaluated on an extensive benchmark comprising most recent methods, demonstrating significant improvement and establishing a new state-of-the-art performance. Our code is publicly available at https://github.com/cuong-dm/ROOT.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 42 of its 71 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

42 of 71 references.

References · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2022Classifier-Free Diffusion Guidancecited by 5,847
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  4. 2013Gaussian Processes for Big Datacited by 383
  5. 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
  6. 2022BBDM: Image-to-image Translation with Brownian Bridge Diffusion Modelscited by 225
  7. 2017Max-value Entropy Search for Efficient Bayesian Optimizationcited by 206
  8. 2013Bayesian Optimization in a Billion Dimensions via Random Embeddingscited by 182
  9. 2019Conditioning by adaptive sampling for robust designcited by 111
  10. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 88
  11. 2019Model Inversion Networks for Model-Based Optimizationcited by 83
  12. 2023Diffusion Models for Black-Box Optimizationcited by 76
30 more
  1. 2019ROBEL: Robotics Benchmarks for Learning with Low-Cost Robotscited by 72
  2. 2017Stochastic Zeroth-order Optimization in High Dimensionscited by 63
  3. 2020Autofocused oracles for model-based designcited by 50
  4. 2021Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spacescited by 45
  5. 2021RoMA: Robust Model Adaptation for Offline Model-based Optimizationcited by 39
  6. 2021Offline Model-Based Optimization via Normalized Maximum Likelihood Estimationcited by 38
  7. 2022Generative Pretraining for Black-Box Optimizationcited by 36
  8. 2022Bidirectional Learning for Offline Infinite-width Model-based Optimizationcited by 35
  9. 2022Data-Driven Offline Decision-Making via Invariant Representation Learningcited by 31
  10. 2023Importance-aware Co-teaching for Offline Model-based Optimizationcited by 28
  11. 2023Parallel-mentoring for Offline Model-based Optimizationcited by 26
  12. 2020Deep Learning in Protein Structural Modeling and Designcited by 25
  13. 2017Decentralized High-Dimensional Bayesian Optimization with Factor Graphscited by 23
  14. 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequencescited by 23
  15. 2023ExPT: Synthetic Pretraining for Few-Shot Experimental Designcited by 22
  16. 2024Offline Model-Based Optimization via Policy-Guided Gradient Searchcited by 19
  17. 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimizationcited by 15
  18. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 15
  19. 2024Offline Model-Based Optimization by Learning to Rankcited by 13
  20. 2015Near-Optimal Active Learning of Multi-Output Gaussian Processescited by 10
  21. 2024Generative Adversarial Model-Based Optimization via Source Critic Regularizationcited by 10
  22. 2024Design Editing for Offline Model-based Optimizationcited by 10
  23. 2025Revisiting Kernel Attention with Correlated Gaussian Process Representationcited by 10
  24. 2024Robust Guided Diffusion for Offline Black-Box Optimizationcited by 8
  25. 2025Boosting Offline Optimizers with Surrogate Sensitivitycited by 6
  26. 2016A Generalized Stochastic Variational Bayesian Hyperparameter Learning Framework for Sparse Spectrum Gaussian Process Regressioncited by 5
  27. 2025Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniquescited by 5
  28. 2020Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processescited by 3
  29. 2017Machine Learning and Manycore Systems Design: A Serendipitous Symbiosiscited by 2
  30. 2016Arch2030: A Vision of Computer Architecture Research over the Next 15 Yearscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026On the Learnability of Offline Model-Based Optimization: A Ranking Perspectivecited by 2
  2. 2026Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimizationcited by 1
  3. 2026Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Taskscited by 0
  4. 2026Rethinking Learnability in Offline Data-driven Optimizationcited by 0