Document Open Access Logo

Nearly Optimal Bounds for Sample-Based Testing and Learning of k-Monotone Functions

Author Hadley Black

PDF
Thumbnail PDF

File

LIPIcs.APPROX-RANDOM.2024.37.pdf
  • Filesize: 1.03 MB
  • 23 pages

Document Identifiers

Author Details

Hadley Black
  • University of California, San Diego, USA

Funding

  • Black, Hadley: This work was done while the author was at UCLA supported by NSF award AF:Small 2007682, NSF Award: Collaborative Research Encore 2217033.

Acknowledgements

We would like to thank Eric Blais and Nathaniel Harms for helpful discussions during the early stages of this work and for their thoughtful feedback. We would also like to thank the anonymous reviewers whose comments helped significantly to improve this write up.

Cite AsGet BibTex

Hadley Black. Nearly Optimal Bounds for Sample-Based Testing and Learning of k-Monotone Functions. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 317, pp. 37:1-37:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/LIPIcs.APPROX/RANDOM.2024.37

Abstract

We study monotonicity testing of functions f : {0,1}^d → {0,1} using sample-based algorithms, which are only allowed to observe the value of f on points drawn independently from the uniform distribution. A classic result by Bshouty-Tamon (J. ACM 1996) proved that monotone functions can be learned with exp(Õ(min{(1/ε)√d,d})) samples and it is not hard to show that this bound extends to testing. Prior to our work the only lower bound for this problem was Ω(√{exp(d)/ε}) in the small ε parameter regime, when ε = O(d^{-3/2}), due to Goldreich-Goldwasser-Lehman-Ron-Samorodnitsky (Combinatorica 2000). Thus, the sample complexity of monotonicity testing was wide open for ε ≫ d^{-3/2}. We resolve this question, obtaining a nearly tight lower bound of exp(Ω(min{(1/ε)√d,d})) for all ε at most a sufficiently small constant. In fact, we prove a much more general result, showing that the sample complexity of k-monotonicity testing and learning for functions f : {0,1}^d → [r] is exp(Ω(min{(rk/ε)√d,d})). For testing with one-sided error we show that the sample complexity is exp(Ω(d)). Beyond the hypercube, we prove nearly tight bounds (up to polylog factors of d,k,r,1/ε in the exponent) of exp(Θ̃(min{(rk/ε)√d,d})) on the sample complexity of testing and learning measurable k-monotone functions f : ℝ^d → [r] under product distributions. Our upper bound improves upon the previous bound of exp(Õ(min{(k/ε²)√d,d})) by Harms-Yoshida (ICALP 2022) for Boolean functions (r = 2).

Subject Classification

ACM Subject Classification
  • Theory of computation → Streaming, sublinear and near linear time algorithms
  • Mathematics of computing → Probabilistic algorithms
Keywords
  • Property testing
  • learning
  • Boolean functions
  • monotonicity
  • k-monotonicity

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Related Versions

References

  1. Nir Ailon and Bernard Chazelle. Information theory in property testing and monotonicity testing in higher dimension. Information and Computation, 204(11):1704-1717, 2006. Google Scholar
  2. Nir Ailon, Bernard Chazelle, Seshadhri Comandur, and Ding Liu. Estimating the distance to a monotone function. Random Structures Algorithms, 31(3):371-383, 2007. Google Scholar
  3. Maria-Florina Balcan, Eric Blais, Avrim Blum, and Liu Yang. Active property testing. In 53rd Annual IEEE Symposium on Foundations of Computer Science, FOCS, 2012. URL: https://doi.org/10.1109/FOCS.2012.64.
  4. Aleksandrs Belovs and Eric Blais. A polynomial lower bound for testing monotonicity. In Proceedings, ACM Symposium on Theory of Computing (STOC), 2016. Google Scholar
  5. Piotr Berman, Meiram Murzabulatov, and Sofya Raskhodnikova. The power and limitations of uniform samples in testing properties of figures. Algorithmica, 81(3):1247-1266, 2019. URL: https://doi.org/10.1007/s00453-018-0467-9.
  6. Piotr Berman, Meiram Murzabulatov, and Sofya Raskhodnikova. Testing convexity of figures under the uniform distribution. Random Struct. Algorithms, 54(3):413-443, 2019. URL: https://doi.org/10.1002/rsa.20797.
  7. Piotr Berman, Sofya Raskhodnikova, and Grigory Yaroslavtsev. L_p-testing. In Proceedings, ACM Symposium on Theory of Computing (STOC), 2014. Google Scholar
  8. Arnab Bhattacharyya. A note on the distance to monotonicity of boolean functions. Technical Report 012, Electronic Colloquium on Computational Complexity (ECCC), 2008. Google Scholar
  9. Arnab Bhattacharyya, Elena Grigorescu, Madhav Jha, Kyoming Jung, Sofya Raskhodnikova, and David Woodruff. Lower bounds for local monotonicity reconstruction from transitive-closure spanners. SIAM Journal on Discrete Mathematics (SIDMA), 26(2):618-646, 2012. Google Scholar
  10. Hadley Black, Eric Blais, and Nathaniel Harms. Testing and learning convex sets in the ternary hypercube. In 15th Innovations in Theoretical Computer Science Conference, ITCS, 2024. URL: https://doi.org/10.4230/LIPICS.ITCS.2024.15.
  11. Hadley Black, Deeparnab Chakrabarty, and C. Seshadhri. A o(d)⋅polylog(n) monotonicity tester for Boolean functions over the hypergrid [n]^d. In Proceedings, ACM-SIAM Symposium on Discrete Algorithms (SODA), 2018. Google Scholar
  12. Hadley Black, Deeparnab Chakrabarty, and C. Seshadhri. Domain reduction for monotonicity testing: A o(d) tester for boolean functions in d-dimensions. In Proceedings of the 2020 ACM-SIAM Symposium on Discrete Algorithms, SODA, 2020. URL: https://doi.org/10.1137/1.9781611975994.122.
  13. Hadley Black, Deeparnab Chakrabarty, and C. Seshadhri. A d^1/2+o(1) monotonicity tester for boolean functions on d-dimensional hypergrids. In 64th IEEE Annual Symposium on Foundations of Computer Science, FOCS, 2023. URL: https://doi.org/10.1109/FOCS57990.2023.00110.
  14. Hadley Black, Deeparnab Chakrabarty, and C. Seshadhri. Directed isoperimetric theorems for boolean functions on the hypergrid and an Õ(n√d) monotonicity tester. In Proceedings of the 55th Annual ACM Symposium on Theory of Computing, STOC, 2023. URL: https://doi.org/10.1145/3564246.3585167.
  15. Hadley Black, Iden Kalemaj, and Sofya Raskhodnikova. Isoperimetric inequalities for real-valued functions with applications to monotonicity testing. Random Structures & Algorithms, 2024. Google Scholar
  16. Eric Blais, Joshua Brody, and Kevin Matulef. Property testing lower bounds via communication complexity. Computational Complexity, 21(2):311-358, 2012. Google Scholar
  17. Eric Blais, Clément L. Canonne, Igor Carboni Oliveira, Rocco A. Servedio, and Li-Yang Tan. Learning circuits with few negations. In RANDOM, 2015. URL: https://doi.org/10.4230/LIPIcs.APPROX-RANDOM.2015.512.
  18. Eric Blais, Renato Ferreira Pinto Jr, and Nathaniel Harms. Vc dimension and distribution-free sample-based testing. In Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, pages 504-517, 2021. Google Scholar
  19. Eric Blais, Sofya Raskhodnikova, and Grigory Yaroslavtsev. Lower bounds for testing properties of functions over hypergrid domains. In Proceedings, IEEE Conference on Computational Complexity (CCC), 2014. Google Scholar
  20. Eric Blais and Yuichi Yoshida. A characterization of constant-sample testable properties. Random Struct. Algorithms, 55(1):73-88, 2019. URL: https://doi.org/10.1002/rsa.20807.
  21. Mark Braverman, Subhash Khot, Guy Kindler, and Dor Minzer. Improved monotonicity testers via hypercube embeddings. In 14th Innovations in Theoretical Computer Science Conference, ITCS, 2023. URL: https://doi.org/10.4230/LIPIcs.ITCS.2023.25.
  22. Jop Briët, Sourav Chakraborty, David García Soriano, and Ari Matsliah. Monotonicity testing and shortest-path routing on the cube. Combinatorica, 32(1):35-53, 2012. Google Scholar
  23. Nader H. Bshouty and Christino Tamon. On the fourier spectrum of monotone functions. J. ACM, 43(4):747-770, 1996. URL: https://doi.org/10.1145/234533.234564.
  24. Clément L. Canonne, Elena Grigorescu, Siyao Guo, Akash Kumar, and Karl Wimmer. Testing k-monotonicity: The rise and fall of boolean functions. Theory Comput., 15:1-55, 2019. URL: https://doi.org/10.4086/toc.2019.v015a001.
  25. Deeparnab Chakrabarty, Kashyap Dixit, Madhav Jha, and C. Seshadhri. Property testing on product distributions: Optimal testers for bounded derivative properties. In Proceedings, ACM-SIAM Symposium on Discrete Algorithms (SODA), 2015. Google Scholar
  26. Deeparnab Chakrabarty and C. Seshadhri. Optimal bounds for monotonicity and Lipschitz testing over hypercubes and hypergrids. In Proceedings, ACM Symposium on Theory of Computing (STOC), 2013. Google Scholar
  27. Deeparnab Chakrabarty and C. Seshadhri. An o(n) monotonicity tester for Boolean functions over the hypercube. SIAM Journal on Computing (SICOMP), 45(2):461-472, 2014. Google Scholar
  28. Deeparnab Chakrabarty and C. Seshadhri. An optimal lower bound for monotonicity testing over hypergrids. Theory of Computing, 10:453-464, 2014. URL: https://doi.org/10.4086/toc.2014.v010a017.
  29. Xi Chen, Anindya De, Yuhao Li, Shivam Nadimpalli, and Rocco A. Servedio. Mildly exponential lower bounds on tolerant testers for monotonicity, unateness, and juntas. In Proceedings of the 2024 ACM-SIAM Symposium on Discrete Algorithms, SODA, 2024. URL: https://doi.org/10.1137/1.9781611977912.151.
  30. Xi Chen, Anindya De, Rocco A. Servedio, and Li-Yang Tan. Boolean function monotonicity testing requires (almost) O(n^1/2) non-adaptive queries. In Proceedings, ACM Symposium on Theory of Computing (STOC), 2015. Google Scholar
  31. Xi Chen, Adam Freilich, Rocco A. Servedio, and Timothy Sun. Sample-based high-dimensional convexity testing. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques, APPROX/RANDOM, 2017. URL: https://doi.org/10.4230/LIPICS.APPROX-RANDOM.2017.37.
  32. Xi Chen, Rocco A. Servedio, and Li-Yang. Tan. New algorithms and lower bounds for monotonicity testing. In Proceedings, IEEE Symposium on Foundations of Computer Science (FOCS), 2014. Google Scholar
  33. Xi Chen, Erik Waingarten, and Jinyu Xie. Beyond talagrand: New lower bounds for testing monotonicity and unateness. In Proceedings, ACM Symposium on Theory of Computing (STOC), 2017. Google Scholar
  34. Yevgeny Dodis, Oded Goldreich, Eric Lehman, Sofya Raskhodnikova, Dana Ron, and Alex Samorodnitsky. Improved testing algorithms for monotonicity. Proceedings, International Workshop on Randomization and Computation (RANDOM), 1999. Google Scholar
  35. Funda Ergun, Sampath Kannan, Ravi Kumar, Ronitt Rubinfeld, and Mahesh Viswanathan. Spot-checkers. J. Comput. System Sci., 60(3):717-751, 2000. Google Scholar
  36. Shahar Fattal and Dana Ron. Approximating the distance to monotonicity in high dimensions. ACM Trans. on Algorithms (TALG), 6(3), 2010. Google Scholar
  37. Renato Ferreira Pinto Jr and Nathaniel Harms. Distribution testing under the parity trace, 2023. URL: https://arxiv.org/abs/2304.01374.
  38. Renato Ferreira Pinto Jr and Nathaniel Harms. Distribution testing with a confused collector. In 15th Innovations in Theoretical Computer Science Conference, ITCS, 2024. URL: https://doi.org/10.4230/LIPICS.ITCS.2024.47.
  39. Eldar Fischer. On the strength of comparisons in property testing. Information and Computation, 189(1):107-116, 2004. Google Scholar
  40. Eldar Fischer, Yonatan Goldhirsh, and Oded Lachish. Partial tests, universal tests and decomposability. In Innovations in Theoretical Computer Science, ITCS. ACM, 2014. URL: https://doi.org/10.1145/2554797.2554841.
  41. Eldar Fischer, Oded Lachish, and Yadu Vasudev. Trading query complexity for sample-based testing and multi-testing scalability. In IEEE 56th Annual Symposium on Foundations of Computer Science, FOCS. IEEE Computer Society, 2015. URL: https://doi.org/10.1109/FOCS.2015.75.
  42. Eldar Fischer, Eric Lehman, Ilan Newman, Sofya Raskhodnikova, and Ronitt Rubinfeld. Monotonicity testing over general poset domains. Proceedings, ACM Symposium on Theory of Computing (STOC), 2002. Google Scholar
  43. Oded Goldreich, Shafi Goldwasser, Eric Lehman, Dana Ron, and Alex Samorodnitsky. Testing monotonicity. Combinatorica, 20:301-337, 2000. Google Scholar
  44. Oded Goldreich, Shafi Goldwasser, and Dana Ron. Property testing and its connection to learning and approximation. Journal of the ACM, 45(4):653-750, 1998. Google Scholar
  45. Oded Goldreich and Dana Ron. On sample-based testers. ACM Trans. Comput. Theory, 8(2):7:1-7:54, 2016. URL: https://doi.org/10.1145/2898355.
  46. Elena Grigorescu, Akash Kumar, and Karl Wimmer. Flipping out with many flips: Hardness of testing k-monotonicity. SIAM J. Discret. Math., 33(4):2111-2125, 2019. URL: https://doi.org/10.1137/18M1217978.
  47. Shirley Halevy and Eyal Kushilevitz. Distribution-free property testing. Proceedings, International Workshop on Randomization and Computation (RANDOM), 2003. Google Scholar
  48. Shirley Halevy and Eyal Kushilevitz. Testing monotonicity over graph products. Random Structures Algorithms, 33(1):44-67, 2008. Google Scholar
  49. Nathaniel Harms and Yuichi Yoshida. Downsampling for testing and learning in product distributions. In 49th International Colloquium on Automata, Languages, and Programming, ICALP 2022, 2022. URL: https://doi.org/10.4230/LIPIcs.ICALP.2022.71.
  50. Michael J. Kearns. Efficient noise-tolerant learning from statistical queries. J. ACM, 45(6):983-1006, 1998. URL: https://doi.org/10.1145/293347.293351.
  51. Michael J. Kearns and Dana Ron. Testing problems with sublearning sample complexity. J. Comput. Syst. Sci., 61(3):428-456, 2000. URL: https://doi.org/10.1006/jcss.1999.1656.
  52. Subhash Khot, Dor Minzer, and Muli Safra. On monotonicity testing and Boolean isoperimetric type theorems. In Proceedings, IEEE Symposium on Foundations of Computer Science (FOCS), 2015. Google Scholar
  53. Subhash Khot, Dor Minzer, and Muli Safra. On monotonicity testing and boolean isoperimetric-type theorems. SIAM J. Comput., 47(6):2238-2276, 2018. URL: https://doi.org/10.1137/16M1065872.
  54. Jane Lange, Ronitt Rubinfeld, and Arsen Vasilyan. Properly learning monotone functions via local correction. In 63rd IEEE Annual Symposium on Foundations of Computer Science, FOCS, 2022. URL: https://doi.org/10.1109/FOCS54457.2022.00015.
  55. Jane Lange and Arsen Vasilyan. Agnostic proper learning of monotone functions: beyond the black-box correction barrier. In 64th IEEE Annual Symposium on Foundations of Computer Science, FOCS, 2023. URL: https://doi.org/10.1109/FOCS57990.2023.00068.
  56. Eric Lehman and Dana Ron. On disjoint chains of subsets. Journal of Combinatorial Theory, Series A, 94(2):399-404, 2001. Google Scholar
  57. Nathan Linial, Yishay Mansour, and Noam Nisan. Constant depth circuits, fourier transform, and learnability. J. ACM, 40(3):607-620, 1993. URL: https://doi.org/10.1145/174130.174138.
  58. Ramesh Krishnan S. Pallavoor, Sofya Raskhodnikova, and Nithin Varma. Parameterized property testing of functions. ACM Trans. Comput. Theory, 9(4):17:1-17:19, 2018. URL: https://doi.org/10.1145/3155296.
  59. Sofya Raskhodnikova. Monotonicity testing. Masters Thesis, MIT, 1999. Google Scholar
  60. Dana Ron, Ronitt Rubinfeld, Muli Safra, and Omri Weinstein. Approximating the Influence of Monotone Boolean Functions in O(√n) Query Complexity. In Proceedings, International Workshop on Randomization and Computation (RANDOM), 2011. Google Scholar
  61. R. Rubinfeld and M. Sudan. Robust characterization of polynomials with applications to program testing. SIAM Journal of Computing, 25:647-668, 1996. Google Scholar
  62. Michael E. Saks and C. Seshadhri. Parallel monotonicity reconstruction. In Proceedings, ACM-SIAM Symposium on Discrete Algorithms (SODA), 2008. Google Scholar
  63. Michel Talagrand. How much are increasing sets positively correlated? Comb., 16(2):243-258, 1996. URL: https://doi.org/10.1007/BF01844850.
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact