mlsanityData to 7 Oct 2026

Offline Multi-Objective Optimization

arXiv 2406.03722 ↗First posted 6 Jun 2024cs.LG cs.AI cs.NEcited by 14

Not on the map. Why?

Abstract (arXiv)

Offline optimization aims to maximize a black-box objective function with a static dataset and has wide applications. In addition to the objective function being black-box and expensive to evaluate, numerous complex real-world problems entail optimizing multiple conflicting objectives, i.e., multi-objective optimization (MOO). Nevertheless, offline MOO has not progressed as much as offline single-objective optimization (SOO), mainly due to the lack of benchmarks like Design-Bench for SOO. To bridge this gap, we propose a first benchmark for offline MOO, covering a range of problems from synthetic to real-world tasks. This benchmark provides tasks, datasets, and open-source examples, which can serve as a foundation for method comparisons and advancements in offline MOO. Furthermore, we analyze how the current related methods can be adapted to offline MOO from four fundamental perspectives, including data, model architecture, learning algorithm, and search algorithm. Empirical results show improvements over the best value of the training set, demonstrating the effectiveness of offline MOO methods. As no particular method stands out significantly, there is still an open challenge in further enhancing the effectiveness of offline MOO. We finally discuss future challenges for offline MOO, with the hope of shedding some light on this emerging field. Our code is available at urlhttps://github.com/lamda-bbo/offline-moo.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 50 of its 90 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

50 of 90 references.

References · 50

  1. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  2. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  3. 2017A Survey on Multi-Task Learningcited by 838
  4. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  5. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  6. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 412
  7. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 340
  8. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  9. 2020pymoo: Multi-objective Optimization in Pythoncited by 196
  10. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  11. 2013Bayesian Optimization in a Billion Dimensions via Random Embeddingscited by 178
  12. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
38 more
  1. 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
  2. 2022Multi-Objective GFlowNetscited by 100
  3. 2022Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoderscited by 99
  4. 2020NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecited by 98
  5. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 96
  6. 2015Predictive Entropy Search for Multi-objective Bayesian Optimizationcited by 88
  7. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 87
  8. 2019Model Inversion Networks for Model-Based Optimizationcited by 83
  9. 2021HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmarkcited by 83
  10. 2021A survey on high-dimensional Gaussian process modeling with application to Bayesian optimizationcited by 76
  11. 2021HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenMLcited by 75
  12. 2023Diffusion Models for Black-Box Optimizationcited by 75
  13. 2020An Easy-to-use Real-world Multi-objective Optimization Problem Suitecited by 71
  14. 2021Few-Shot Bayesian Optimization with Deep Kernel Surrogatescited by 70
  15. 2020Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarkscited by 67
  16. 2021NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learningcited by 63
  17. 2019Multi-objective Bayesian Optimization using Pareto-frontier Entropycited by 57
  18. 2022Joint Entropy Search for Maximally-Informed Bayesian Optimizationcited by 55
  19. 2022Pareto Set Learning for Expensive Multi-Objective Optimizationcited by 51
  20. 2021RoMA: Robust Model Adaptation for Offline Model-based Optimizationcited by 39
  21. 2022Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimizationcited by 37
  22. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RLcited by 36
  23. 2022Bidirectional Learning for Offline Infinite-width Model-based Optimizationcited by 35
  24. 2022Data-Driven Offline Decision-Making via Invariant Representation Learningcited by 31
  25. 2023Importance-aware Co-teaching for Offline Model-based Optimizationcited by 28
  26. 2023Parallel-mentoring for Offline Model-based Optimizationcited by 26
  27. 2024Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Modelscited by 24
  28. 2023Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequencescited by 23
  29. 2024Offline Model-Based Optimization via Policy-Guided Gradient Searchcited by 19
  30. 2021Bayesian Optimization over Permutation Spacescited by 17
  31. 2022The Weights can be Harmful: Pareto Search versus Weighted Search in Multi-Objective Search-Based Software Engineeringcited by 17
  32. 2022Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessmentcited by 17
  33. 2022Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spacescited by 14
  34. 2023Neural Multi-Objective Combinatorial Optimization with Diversity Enhancementcited by 13
  35. 2021Multi-objective Optimization by Learning Space Partitionscited by 8
  36. 2023Stochastic Population Update Can Provably Be Helpful in Multi-Objective Evolutionary Algorithmscited by 8
  37. 2024"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihoodcited by 8
  38. 2013Analyzing Evolutionary Optimization in Noisy Environmentscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 5.

14 papers.

Sort:

By area:

  1. 2024ParetoFlow: Guided Flows in Multi-Objective Optimizationcited by 17
  2. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 14
  3. 2024Offline Model-Based Optimization by Learning to Rankcited by 13
  4. 2025Preference-Guided Diffusion for Multi-Objective Offline Optimizationcited by 12
  5. 2025Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddingscited by 6
  6. 2025BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placementcited by 4
  7. 2025FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimizationcited by 2
  8. 2025SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusioncited by 2
  9. 2026Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimizationcited by 2
  10. 2025Learning Design-Score Manifold to Guide Diffusion Models for Offline Optimizationcited by 1
  11. 2026The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimizationcited by 0
  12. 2026Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimizationcited by 0
2 more
  1. 2026Rethinking Learnability in Offline Data-driven Optimizationcited by 0
  2. 2026ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto Frontcited by 0