Papers
Topics
Authors
Recent
Search
2000 character limit reached

Error-Tolerant Exact Query Learning of Finite Set Partitions with Same-Cluster Oracle

Published 22 May 2023 in cs.DS, cs.LG, and stat.ML | (2305.13402v2)

Abstract: This paper initiates the study of active learning for exact recovery of partitions exclusively through access to a same-cluster oracle in the presence of bounded adversarial error. We first highlight a novel connection between learning partitions and correlation clustering. Then we use this connection to build a R\'enyi-Ulam style analytical framework for this problem, and prove upper and lower bounds on its worst-case query complexity. Further, we bound the expected performance of a relevant randomized algorithm. Finally, we study the relationship between adaptivity and query complexity for this problem and related variants.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. H. Abasi and B. Nader. On learning graphs with edge-detecting queries. In Algorithmic Learning Theory, pages 3–30. PMLR, 2019.
  2. Aggregating inconsistent information: ranking and clustering. Journal of the ACM (JACM), 55(5):1–27, 2008.
  3. Approximate correlation clustering using same-cluster queries. In LATIN 2018: Theoretical Informatics: 13th Latin American Symposium, Buenos Aires, Argentina, April 16-19, 2018, Proceedings, pages 14–27. Springer, 2018.
  4. N. Alon and V. Asodi. Learning a hidden subgraph. SIAM Journal on Discrete Mathematics, 18(4):697–712, 2005.
  5. N. Alon and J. H. Spencer. The probabilistic method. John Wiley & Sons, 2016.
  6. Learning a hidden matching. SIAM Journal on Computing, 33(2):487–501, 2004.
  7. S. Angelopoulos and S. Kamali. R\\\backslash\’enyi-ulam games and online computation with imperfect advice. arXiv preprint arXiv:2301.01631, 2023.
  8. D. Angluin and J. Chen. Learning a hidden graph using o (logn) queries per edge. Journal of Computer and System Sciences, 74(4):546–556, 2008.
  9. Clustering with same-cluster queries. Advances in neural information processing systems, 29, 2016.
  10. A comparative survey of non-adaptive pooling designs. In Genetic mapping and DNA sequencing, pages 133–154. Springer, 1996.
  11. Correlation clustering. In The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings., pages 238–247. IEEE, 2002.
  12. Combinatorial search on graphs motivated by bioinformatics applications: A brief survey. In Graph-Theoretic Concepts in Computer Science: 31st International Workshop, WG 2005, Metz, France, June 23-25, 2005, Revised Selected Papers 31, pages 16–27. Springer, 2005.
  13. Exact recovery of mangled clusters with same-cluster queries. Advances in Neural Information Processing Systems, 33:9324–9334, 2020.
  14. On margin-based cluster recovery with oracle queries. Advances in Neural Information Processing Systems, 34:25231–25243, 2021.
  15. Learning a hidden graph. Optimization Letters, 8:2341–2348, 2014.
  16. F. Cicalese. Variations on a theme of ulam and rényi: More types of questions and lies. Fault-Tolerant Search Algorithms: Reliable Computation with Unreliable Information, pages 77–98, 2013.
  17. F. Cicalese. Perfect strategies for the ulam-rényi game with multi-interval questions. Theory of Computing Systems, 54:578–594, 2014.
  18. F. Cicalese and M. Rossi. On the multi-interval ulam-rényi game: For 3 lies 4 intervals suffice. Theoretical Computer Science, 809:339–356, 2020.
  19. Ulam’s searching game with lies. Journal of Combinatorial Theory, Series A, 52(1):62–76, 1989.
  20. N. G. De Bruijn. Asymptotic methods in analysis, volume 4. Courier Corporation, 1981.
  21. Clustering with queries under semi-random noise. In Conference on Learning Theory, pages 5278–5313. PMLR, 2022.
  22. Correlation clustering in general weighted graphs. Theoretical Computer Science, 361(2-3):172–187, 2006.
  23. C. Deppe. Solution of ulam’s searching game with three lies or an optimal adaptive strategy for binary three-error-correcting codes. Discrete Mathematics, 224(1-3):79–98, 2000.
  24. I. Giotis and V. Guruswami. Correlation clustering with a fixed number of clusters. Theory OF Computing, 2:249–266, 2006.
  25. V. Grebinski and G. Kucherov. Reconstructing a hamiltonian cycle by querying the graph: Application to dna physical mapping. Discrete Applied Mathematics, 88(1-3):147–165, 1998.
  26. V. Grebinski and G. Kucherov. Optimal reconstruction of graphs under the additive model. Algorithmica, 28:104–124, 2000.
  27. Clustering with a faulty oracle. In Proceedings of The Web Conference 2020, pages 2831–2834, 2020.
  28. M. Gupta and R. Y. Zhang. The optimal error resilience of interactive communication over binary channels. In Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing, pages 948–961, 2022.
  29. Binary error-correcting codes with minimal noiseless feedback. arXiv preprint arXiv:2212.05673, 2022.
  30. Essential Coding Theory. 2022.
  31. Communication with partial noiseless feedback. In Approximation, randomization, and combinatorial optimization. Algorithms and techniques (APPROX/RANDOM 2015). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, 2015.
  32. The solution of a problem of ulam on searching with lies. In Proceedings. 1998 IEEE International Symposium on Information Theory (Cat. No. 98CH36252), page 244. IEEE, 1998.
  33. X. Liu and S. Mukherjee. Tight query complexity bounds for learning graph partitions. In Conference on Learning Theory, pages 167–181. PMLR, 2022.
  34. Bilu–linial stable instances of max cut and minimum multiway cut. In Proceedings of the twenty-fifth annual ACM-SIAM symposium on Discrete algorithms, pages 890–906. SIAM, 2014.
  35. Correlation clustering with noisy partial information. In Conference on Learning Theory, pages 1321–1342. PMLR, 2015.
  36. C. Marini and F. Montagna. Probabilistic variants of renyi-ulam game and many-valued logic. Task Quarterly, 9(3):317–335, 2005.
  37. C. Mathieu and W. Schudy. Correlation clustering with noisy input. In Proceedings of the twenty-first annual ACM-SIAM symposium on Discrete Algorithms, pages 712–728. SIAM, 2010.
  38. A. Mazumdar and B. Saha. Clustering with noisy queries. Advances in Neural Information Processing Systems, 30, 2017.
  39. A. Pelc. Solution of ulam’s problem on searching with a lie. Journal of Combinatorial Theory, Series A, 44(1):129–140, 1987.
  40. A. Pelc. Searching with known error probability. Theoretical Computer Science, 63(2):185–202, 1989.
  41. A. Pelc. Searching games with errors—fifty years of coping with liars. Theoretical Computer Science, 270(1-2):71–109, 2002.
  42. P. Peng and J. Zhang. Towards a query-optimal and time-efficient algorithm for clustering with a faulty oracle. In Conference on Learning Theory, pages 3662–3680. PMLR, 2021.
  43. On stirling numbers of the second kind. Journal of Combinatorial Theory, 7(2):116–121, 1969.
  44. L. Reyzin and N. Srivastava. Learning and verifying graphs using queries with a focus on edge counting. International Conference on Algorithmic Learning Theory, page 285–297, 2007.
  45. Coping with errors in binary search procedures (preliminary report). In Proceedings of the tenth annual ACM symposium on Theory of computing, pages 227–232, 1978.
  46. B. Saha and S. Subramanian. Correlation clustering with same-cluster queries bounded by optimal cost. In 27th Annual European Symposium on Algorithms (ESA 2019), volume 144, page 81. Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 2019.
  47. X. Shaoji. The size of uniquely colorable graphs. Journal of Combinatorial Theory, Series B, 50(2):319–320, 1990.
  48. A new approach using multiplex long accurate pcr and yeast artificial chromosomes for bacterial chromosome mapping and sequencing. Genome research, 6(5):448–453, 1996.
  49. J. Spencer. Guess a number—with lying. Mathematics Magazine, 57(2):105–108, 1984.
  50. J. Spencer. Ulam’s searching game with a fixed number of lies. Theoretical Computer Science, 95(2):307–321, 1992.
  51. S. M. Ulam. Adventures of a Mathematician. Univ of California Press, 1991.
  52. Graph learning: A survey. IEEE Transactions on Artificial Intelligence, 2(2):109–127, apr 2021. doi: 10.1109/tai.2021.3076021. URL https://doi.org/10.1109%2Ftai.2021.3076021.
Citations (1)
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 haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

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

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up