Online Covering with Multiple Experts (2312.14564v1)
Abstract: Designing online algorithms with machine learning predictions is a recent technique beyond the worst-case paradigm for various practically relevant online problems (scheduling, caching, clustering, ski rental, etc.). While most previous learning-augmented algorithm approaches focus on integrating the predictions of a single oracle, we study the design of online algorithms with \emph{multiple} experts. To go beyond the popular benchmark of a static best expert in hindsight, we propose a new \emph{dynamic} benchmark (linear combinations of predictions that change over time). We present a competitive algorithm in the new dynamic benchmark with a performance guarantee of $O(\log K)$, where $K$ is the number of experts, for $0-1$ online optimization problems. Furthermore, our multiple-expert approach provides a new perspective on how to combine in an online manner several online algorithms - a long-standing central subject in the online algorithm research community.
- Online facility location with multiple advice. In Advances in Neural Information Processing Systems, volume 34, pages 4661–4673, 2021.
- Online algorithms with multiple predictions. In Proc. 39th International Conference on Machine Learning, 2022.
- Online Computation with Untrusted Advice. In 11th Innovations in Theoretical Computer Science Conference (ITCS 2020), volume 151, pages 52:1–52:15, 2020.
- Online metric algorithms with untrusted predictions. In International Conference on Machine Learning, pages 345–355, 2020.
- Mixing predictions for online metric algorithms, 2023. arXiv:2304.01781.
- On-line choice of on-line algorithms. In Symposium of Discrete Algorithms (SODA), pages 432–440, 1993.
- The primal-dual method for learning augmented algorithms. In Advances in Neural Information Processing Systems, volume 33, pages 20083–20094, 2020.
- On-line learning and the metrical task system problem. Machine Learning, 39(1):35–58, 2000.
- Metrical task systems on trees via mirror descent and unfair gluing. SIAM Journal on Computing, 50(3):909–923, 2021.
- K-server via multiscale entropic regularization. In Proc. 50th Symposium on Theory of Computing, pages 3–16, 2018.
- Competitive analysis via regularization. In Proc. 25th Symposium on Discrete Algorithms, pages 436–444, 2014.
- k-servers with a smile: Online algorithms via projections. In Proc. 30th Symposium on Discrete Algorithms, pages 98–116, 2019.
- Algorithms with prediction portfolios. In Advances in Neural Information Processing Systems, 2022.
- Online algorithms for rent-or-buy with expert advice. In International Conference on Machine Learning, pages 2319–2327, 2019.
- Online algorithms for rent-or-buy with expert advice. In Proceedings of the 36th International Conference on Machine Learning, 2019.
- Learning-based frequency estimation algorithms. In Proc. Conference on Learning Representations, 2019.
- Primal-dual algorithms with predictions for online bounded allocation and ad-auctions problems. In International Conference on Algorithmic Learning Theory, pages 891–908, 2023.
- The case for learned index structures. In Proc. Conference on Management of Data, pages 489–504, 2018.
- Improving online algorithms via ML predictions. In Proc. 32nd Conference on Neural Information Processing Systems, pages 9684–9693, 2018.
- Online scheduling via learned weights. In Proc. Symposium on Discrete Algorithms, pages 1859–1877, 2020.
- Competitive caching with machine learned advice. In International Conference on Machine Learning, pages 3296–3305, 2018.
- Michael Mitzenmacher. A model for learned bloom filters, and optimizing by sandwiching. In Proc. Conference on Neural Information Processing Systems, pages 464–473, 2018.
- Michael Mitzenmacher. Scheduling with predictions and the price of misprediction. In Proc. 11th Innovations in Theoretical Computer Science Conference, 2020.
- Beyond the Worst-Case Analysis of Algorithms, chapter Algorithms with Predictions. Cambridge University Press, 2020.
- Dhruv Rohatgi. Near-optimal bounds for online caching with machine learned advice. In Proc. Symposium on Discrete Algorithms, pages 1834–1845, 2020.