Papers
Topics
Authors
Recent
Search
2000 character limit reached

LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch

Published 4 Sep 2024 in cs.MS, cs.LG, and math.OC | (2409.02969v3)

Abstract: Multiobjective optimization problems (MOPs) are prevalent in machine learning, with applications in multi-task learning, learning under fairness or robustness constraints, etc. Instead of reducing multiple objective functions into a scalar objective, MOPs aim to optimize for the so-called Pareto optimality or Pareto set learning, which involves optimizing more than one objective function simultaneously, over models with thousands / millions of parameters. Existing benchmark libraries for MOPs mainly focus on evolutionary algorithms, most of which are zeroth-order / meta-heuristic methods that do not effectively utilize higher-order information from objectives and cannot scale to large-scale models with thousands / millions of parameters. In light of the above gap, this paper introduces LibMOON, the first multiobjective optimization library that supports state-of-the-art gradient-based methods, provides a fair benchmark, and is open-sourced for the community.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Inherent tradeoffs in learning fair representations. The Journal of Machine Learning Research, 23(1):2527–2552, 2022.
  2. Fair and optimal classification via post-processing. In International Conference on Machine Learning, pages 37977–38012. PMLR, 2023.
  3. Multi-controller multi-objective locomotion planning for legged robots. In 2019 IEEE/RSJ international conference on intelligent robots and systems (IROS), pages 4714–4721. IEEE, 2019.
  4. Prediction-guided multi-objective reinforcement learning for continuous robot control. In International conference on machine learning, pages 10607–10616. PMLR, 2020.
  5. Dietmar Jannach. Multi-objective recommender systems: Survey and challenges. arXiv preprint arXiv:2210.10309, 2022.
  6. Multiobjective deep reinforcement learning for recommendation systems. IEEE Access, 10:65011–65027, 2022.
  7. Multi-objective optimization with recommender systems: A systematic review. Information Systems, 117:102233, 2023.
  8. Matthias Ehrgott. Multicriteria optimization, volume 491. Springer Science & Business Media, 2005.
  9. Platemo: A matlab platform for evolutionary multi-objective optimization [educational forum]. IEEE Computational Intelligence Magazine, 12(4):73–87, 2017.
  10. A parallel global multiobjective framework for optimization: pagmo. Journal of Open Source Software, 5(53):2338, 2020.
  11. Generating well-spaced points on a unit simplex for evolutionary many-objective optimization. IEEE Transactions on Evolutionary Computation, 25(1):48–60, 2020.
  12. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, 31, 2018.
  13. Pareto multi-task learning. Advances in neural information processing systems, 32, 2019.
  14. Gradient-based multiobjective optimization with uncertainties. In NEO 2016: Results of the Numerical and Evolutionary Optimization Workshop NEO 2016 and the NEO Cities 2016 Workshop held on September 20-24, 2016 in Tlalnepantla, Mexico, pages 159–182. Springer, 2018.
  15. Pytorch. Programming with TensorFlow: Solution for Edge Computing Applications, pages 87–104, 2021.
  16. Multi-task learning with user preferences: Gradient descent with controlled ascent in pareto optimization. In International Conference on Machine Learning, pages 6597–6607. PMLR, 2020.
  17. Profiling pareto front with multi-objective stein variational gradient descent. Advances in Neural Information Processing Systems, 34:14721–14733, 2021.
  18. Learning the pareto front with hypernetworks. arXiv preprint arXiv:2010.04104, 2020.
  19. Controllable pareto multi-task learning. arXiv preprint arXiv:2010.06313, 2020.
  20. Convex optimization. Cambridge university press, 2004.
  21. Panacea: Pareto alignment via preference adaptation for llms. arXiv preprint arXiv:2402.02030, 2024.
  22. Smooth tchebycheff scalarization for multi-objective optimization. In International conference on machine learning. PMLR, 2024.
  23. Pareto set learning for expensive multi-objective optimization. Advances in Neural Information Processing Systems, 35:19231–19247, 2022.
  24. Baijiong Lin and Yu Zhang. Libmtl: A python library for deep multi-task learning. The Journal of Machine Learning Research, 24(1):9999–10005, 2023.
  25. The jmetal framework for multi-objective optimization: Design and architecture. In IEEE Congress on Evolutionary Computation, pages 1–8, 2010.
  26. J. Blank and K. Deb. pymoo: Multi-objective optimization in python. IEEE Access, 8:89497–89509, 2020.
  27. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part i: Solving problems with box constraints. IEEE Transactions on Evolutionary Computation, 18(4):577–601, 2014.
  28. An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, part ii: Handling constraints and extending to an adaptive approach. IEEE Transactions on Evolutionary Computation, 18(4):602–622, 2014.
  29. Moea/d: A multiobjective evolutionary algorithm based on decomposition. IEEE Transactions on evolutionary computation, 11(6):712–731, 2007.
  30. Sms-emoa: Multiobjective selection based on dominated hypervolume. European Journal of Operational Research, 181(3):1653–1669, 2007.
  31. Evotorch: Scalable evolutionary computation in python. arXiv preprint arXiv:2302.12600, 2023.
  32. Evox: A distributed gpu-accelerated framework for scalable evolutionary computation. IEEE Transactions on Evolutionary Computation, 2024.
  33. Scalable pareto front approximation for deep multi-objective learning. In 2021 IEEE international conference on data mining (ICDM), pages 1306–1311. IEEE, 2021.
  34. Revisiting scalarization in multi-task learning: A theoretical perspective. arXiv preprint arXiv:2308.13985, 2023.
  35. Addressing fairness in classification with a model-agnostic multi-objective algorithm. In Uncertainty in artificial intelligence, pages 600–609. PMLR, 2021.
  36. Kaisa Miettinen. Nonlinear multiobjective optimization, volume 12. Springer Science & Business Media, 1999.
  37. Multi-objective learning to predict pareto fronts using hypervolume maximization. arXiv preprint arXiv:2102.04523, 2021.
  38. Pmgda: A preference-based multiple gradient descent algorithm. arXiv preprint arXiv:2402.09492, 2024.
  39. Reasonable effectiveness of random weighting: A litmus test for multi-task learning. arXiv preprint arXiv:2111.10603, 2021.
  40. On tchebycheff decomposition approaches for multiobjective evolutionary optimization. IEEE Transactions on Evolutionary Computation, 22(2):226–244, 2017.
  41. Time complexity and zeros of the hypervolume indicator gradient field. In EVOLVE-a bridge between probability, set oriented numerics, and evolutionary computation III, pages 169–193. Springer, 2014.
  42. Evolution strategies–a comprehensive introduction. Natural computing, 1:3–52, 2002.
  43. Evolutionary pareto set learning with structure constraints. arXiv preprint arXiv:2310.20426, 2023.
  44. Efficient pareto manifold learning with low-rank structure. arXiv preprint arXiv:2407.20734, 2024.
  45. Pareto low-rank adapters: Efficient multi-task learning with preferences. arXiv preprint arXiv:2407.08056, 2024.
  46. Hypernetworks. arXiv preprint arXiv:1609.09106, 2016.
  47. Botorch: A framework for efficient Monte-Carlo Bayesian optimization. Advances in neural information processing systems, 33:21524–21538, 2020.
  48. HEBO: Pushing the limits of sample-efficient hyperparameter optimisation. Journal of Artificial Intelligence Research, 74, 07 2022.
  49. Hypervolume-guided decomposition for parallel expensive multiobjective optimization. IEEE Transactions on Evolutionary Computation, 28(2):432–444, 2024.
  50. An efficient batch expensive multi-objective evolutionary algorithm based on decomposition. In 2017 IEEE Congress on Evolutionary Computation (CEC), pages 1343–1349, 2017.
  51. A flexible framework for multi-objective bayesian optimization using random scalarizations. In Uncertainty in Artificial Intelligence, pages 766–776. PMLR, 2020.
  52. On the parameter setting of the penalty-based boundary intersection method in moea/d. In International Conference on Evolutionary Multi-Criterion Optimization, pages 413–423. Springer, 2021.
  53. The hypervolume indicator: Problems and algorithms. arXiv preprint arXiv:2005.00515, 2020.
  54. Modified distance calculation in generational distance and inverted generational distance. In Evolutionary Multi-Criterion Optimization: 8th International Conference, EMO 2015, Guimarães, Portugal, March 29–April 1, 2015. Proceedings, Part II 8, pages 110–125. Springer, 2015.
  55. Umoea/d: A multiobjective evolutionary algorithm for uniform pareto objectives based on decomposition. arXiv preprint arXiv:2402.09486, 2024.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We found no open problems mentioned in this paper.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now