mlsanityData to 14 Oct 2026

Model Inversion Networks for Model-Based Optimization

arXiv 1912.13464 ↗First posted 31 Dec 2019cs.LG stat.MLcited by 83

Not on the map. Why?

Abstract (arXiv)

In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein sequences or valid natural images), such model-based optimization problems become exceptionally difficult, since the optimizer must avoid out-of-distribution and invalid inputs. We propose to address such problem with model inversion networks (MINs), which learn an inverse mapping from scores to inputs. MINs can scale to high-dimensional input spaces and leverage offline logged data for both contextual and non-contextual optimization problems. MINs can also handle both purely offline data sources and active data collection. We evaluate MINs on tasks from the Bayesian optimization literature, high-dimensional model-based optimization problems over images and protein designs, and contextual bandit optimization from logged data.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 14; 2024: 24; 2025: 14; 2026: 13.

83 papers.

Sort:

By area:

  1. 2022Biological Sequence Design with GFlowNetscited by 174
  2. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 97
  3. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 88
  4. 2023Diffusion Models for Black-Box Optimizationcited by 76
  5. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 73
  6. 2021RoMA: Robust Model Adaptation for Offline Model-based Optimizationcited by 39
  7. 2022How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspectivecited by 39
  8. 2021Offline Model-Based Optimization via Normalized Maximum Likelihood Estimationcited by 38
  9. 2022Generative Pretraining for Black-Box Optimizationcited by 36
  10. 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraintscited by 35
  11. 2022Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxationcited by 32
  12. 2022Data-Driven Offline Decision-Making via Invariant Representation Learningcited by 31
38 more
  1. 2021Data-Driven Offline Optimization For Architecting Hardware Acceleratorscited by 29
  2. 2024Recent Advances on Machine Learning for Computational Fluid Dynamics: A Surveycited by 28
  3. 2023Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learningcited by 26
  4. 2024Diffusion Model for Data-Driven Black-Box Optimizationcited by 24
  5. 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequencescited by 23
  6. 2023ExPT: Synthetic Pretraining for Few-Shot Experimental Designcited by 22
  7. 2024GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learningcited by 22
  8. 2024DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimizationcited by 20
  9. 2024Offline Model-Based Optimization via Policy-Guided Gradient Searchcited by 19
  10. 2021Deep Extrapolation for Attribute-Enhanced Generationcited by 18
  11. 2022Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMCcited by 17
  12. 2024Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimizationcited by 15
  13. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 15
  14. 2024SurfPro: Functional Protein Design Based on Continuous Surfacecited by 14
  15. 2024Offline Multi-Objective Optimizationcited by 14
  16. 2021Adaptive machine learning for protein engineeringcited by 13
  17. 2024Improved Off-policy Reinforcement Learning in Biological Sequence Designcited by 13
  18. 2024Offline Model-Based Optimization by Learning to Rankcited by 13
  19. 2025Posterior Inference with Diffusion Models for High-dimensional Black-box Optimizationcited by 13
  20. 2023Importance Weighted Expectation-Maximization for Protein Sequence Designcited by 12
  21. 2025Preference-Guided Diffusion for Multi-Objective Offline Optimizationcited by 12
  22. 2024Functional Graphical Models: Structure Enables Offline Data-Driven Optimizationcited by 11
  23. 2024Design Editing for Offline Model-based Optimizationcited by 10
  24. 2023Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimizationcited by 8
  25. 2024"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihoodcited by 8
  26. 2024Network Inversion of Convolutional Neural Netscited by 8
  27. 2024Robust Guided Diffusion for Offline Black-Box Optimizationcited by 8
  28. 2025Simplifying Bayesian Optimization Via In-Context Direct Optimum Samplingcited by 7
  29. 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 7
  30. 2022Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learningcited by 6
  31. 2025Boosting Offline Optimizers with Surrogate Sensitivitycited by 6
  32. 2024Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substratescited by 5
  33. 2025Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniquescited by 5
  34. 2025Posterior Inference in Latent Space for Scalable Constrained Black-box Optimizationcited by 5
  35. 2022Forecasting labels under distribution-shift for machine-guided sequence designcited by 4
  36. 2023Diffusing Gaussian Mixtures for Generating Categorical Datacited by 4
  37. 2023Latent Conservative Objective Models for Data-Driven Crystal Structure Predictioncited by 4
  38. 2025ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridgecited by 4

50 most cited of 83 All 83 (JSON)