Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Online Algorithms with Uncertainty-Quantified Predictions (2310.11558v2)

Published 17 Oct 2023 in cs.LG and cs.DS

Abstract: The burgeoning field of algorithms with predictions studies the problem of using possibly imperfect machine learning predictions to improve online algorithm performance. While nearly all existing algorithms in this framework make no assumptions on prediction quality, a number of methods providing uncertainty quantification (UQ) on machine learning models have been developed in recent years, which could enable additional information about prediction quality at decision time. In this work, we investigate the problem of optimally utilizing uncertainty-quantified predictions in the design of online algorithms. In particular, we study two classic online problems, ski rental and online search, where the decision-maker is provided predictions augmented with UQ describing the likelihood of the ground truth falling within a particular range of values. We demonstrate that non-trivial modifications to algorithm design are needed to fully leverage the UQ predictions. Moreover, we consider how to utilize more general forms of UQ, proposing an online learning framework that learns to exploit UQ to make decisions in multi-instance settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information Fusion, 76:243–297, dec 2021.
  2. Thompson sampling for contextual bandits with linear payoffs, 2014.
  3. Online learning with feedback graphs: Beyond bandits. In Conference on Learning Theory, pages 23–35. PMLR, 2015.
  4. Customizing ML Predictions for Online Algorithms. In Proceedings of the 37th International Conference on Machine Learning, pages 303–313. PMLR, November 2020.
  5. Online metric algorithms with untrusted predictions. In International Conference on Machine Learning, pages 345–355. PMLR, 2020.
  6. Secretary and online matching problems with machine learned advice. Advances in Neural Information Processing Systems, 33:7933–7944, 2020.
  7. Single-leg revenue management with advice. In Proceedings of the 24th ACM Conference on Economics and Computation, EC ’23, page 207, New York, NY, USA, 2023. Association for Computing Machinery.
  8. Online decision making with high-dimensional covariates. Oper. Res., 68(1):276–294, jan 2020.
  9. Beyond IID: Data-driven decision-making in heterogeneous environments. In Advances in Neural Information Processing Systems, May 2022.
  10. Online Learning with Imperfect Hints. In Proceedings of the 37th International Conference on Machine Learning, pages 822–831. PMLR, November 2020.
  11. Online computation and competitive analysis. cambridge university press, 2005.
  12. Optimal robustness-consistency tradeoffs for learning-augmented metrical task systems. In International Conference on Artificial Intelligence and Statistics, pages 9377–9399. PMLR, 2023.
  13. Online Learning with a Hint. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.
  14. Learning online algorithms with distributional advice. In International Conference on Machine Learning, pages 2687–2696. PMLR, 2021.
  15. Ran El-Yaniv. Competitive solutions for online financial problems. ACM Computing Surveys (CSUR), 30(1):28–69, 1998.
  16. Optimal search and one-way trading online algorithms. Algorithmica, 30:101–139, 2001.
  17. Nonparametric stochastic contextual bandits, 2018.
  18. Augmenting online algorithms with ε𝜀\varepsilonitalic_ε-accurate predictions. Advances in Neural Information Processing Systems, 35:2115–2127, 2022.
  19. Online learning with prior knowledge. In Nader H. Bshouty and Claudio Gentile, editors, Learning Theory, pages 499–513, Berlin, Heidelberg, 2007. Springer Berlin Heidelberg.
  20. Online knapsack with frequency predictions. Advances in Neural Information Processing Systems, 34:2733–2743, 2021.
  21. Online selection problems against constrained adversary. In International Conference on Machine Learning, pages 5002–5012. PMLR, 2021.
  22. Dynamic tcp acknowledgement and other stories about e/(e-1). In Proceedings of the thirty-third annual ACM symposium on Theory of computing, pages 502–509, 2001.
  23. Competitive randomized algorithms for non-uniform problems. In Proceedings of the first annual ACM-SIAM symposium on Discrete algorithms, pages 301–309, 1990.
  24. Competitive snoopy caching. Algorithmica, 3:79–119, 1988.
  25. An optimal algorithm for on-line bipartite matching. In Proceedings of the twenty-second annual ACM symposium on Theory of computing, pages 352–358, 1990.
  26. The constrained ski-rental problem and its application to online cloud cost optimization. In 2013 Proceedings IEEE INFOCOM, pages 1492–1500. IEEE, 2013.
  27. Learning predictions for algorithms with predictions, 2022.
  28. Locally-adaptive nonparametric online learning, 2020.
  29. Stochastic linear bandits with hidden low rank structure, 2019.
  30. Online scheduling via learned weights. In Proceedings of the Fourteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pages 1859–1877. SIAM, 2020.
  31. A contextual-bandit approach to personalized news article recommendation. In Proceedings of the 19th international conference on World wide web. ACM, apr 2010.
  32. Optimal algorithms for k-search with application in option pricing. Algorithmica, 55(2):311–328, 2009.
  33. Competitive caching with machine learned advice. Journal of the ACM (JACM), 68(4):1–25, 2021.
  34. Online Optimization with Uncertain Information. ACM Transactions on Algorithms, 8(1):1–29, January 2012.
  35. Using ai uncertainty quantification to improve human decision-making. arXiv preprint arXiv:2309.10852, 2023.
  36. H. Brendan McMahan. A survey of algorithms and analysis for adaptive online learning, 2015.
  37. Algorithms with predictions, 2020.
  38. Algorithms with predictions. Communications of the ACM, 65(7):33–35, 2022.
  39. Randomized algorithms. ACM Computing Surveys (CSUR), 28(1):33–37, 1996.
  40. Inductive confidence machines for regression. In European Conference on Machine Learning, 2002.
  41. Improving online algorithms via ml predictions. Advances in Neural Information Processing Systems, 31, 2018.
  42. Online learning with predictable sequences. In Conference on Learning Theory, pages 993–1019. PMLR, 2013.
  43. Nonparametric bandits with covariates, 2010.
  44. Shai Shalev-Shwartz. Online learning and online convex optimization. Found. Trends Mach. Learn., 4(2):107–194, feb 2012.
  45. Aleksandrs Slivkins. Contextual bandits with similarity information, 2014.
  46. Pareto-optimal learning-augmented algorithms for online conversion problems. Advances in Neural Information Processing Systems, 34:10339–10350, 2021.
  47. Competitive algorithms for the online multiple knapsack problem with application to electric vehicle charging. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 4(3):1–32, 2020.
  48. Conformal predictive decision making. In Conformal and Probabilistic Prediction and Applications, pages 52–62. PMLR, 2018.
  49. Algorithmic Learning in a Random World. Springer-Verlag, Berlin, Heidelberg, 2005.
  50. Machine-learning applications of algorithmic randomness. In Proceedings of the Sixteenth International Conference on Machine Learning, ICML ’99, page 444–453, San Francisco, CA, USA, 1999. Morgan Kaufmann Publishers Inc.
  51. Nonparametric contextual bandits in an unknown metric space, 2019.
  52. Optimal robustness-consistency trade-offs for learning-augmented online algorithms. Advances in Neural Information Processing Systems, 33:8042–8053, 2020.
  53. Online learning with side information. In MILCOM 2017 - 2017 IEEE Military Communications Conference (MILCOM), pages 303–308, Baltimore, MD, October 2017. IEEE.
  54. Randomized Allocation with nonparametric estimation for a multi-armed bandit problem with covariates. The Annals of Statistics, 30(1):100 – 121, 2002.
  55. Peak-aware online economic dispatching for microgrids. In Proceedings of the 2015 ACM Sixth International Conference on Future Energy Systems, pages 27–36, 2015.
  56. The primal-dual method for learning augmented algorithms, 2020.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now