The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Constant depth circuits, Fourier transform, and learnability
Open accessAbstract
In this paper, Boolean functions in ,4C0 are studied using harmonic analysis on the cube.The main result is that an ACO Boolean function has almost all of its "power spectrum" on the low-order coefficients.An important ingredient of the proof is Hastad's switching lemma [8].This result implies several new properties of functions in -4C[': Functions in AC() have low "average sensitivity;" they may be approximated well by a real polynomial of low degree and they cannot be pseudorandom function generators.Perhaps the most interesting application is an O(n POIYIOg(n ')-time algorithm for learning functions in ACO.The algorithm observes the behavior of an AC'" function on O(nPO'Y'Og(n)) randomly chosen inputs, and derives a good approximation for the Fourier transform of the function.This approximation allows the algorithm to predict, with high probability, the value of the function on other randomly chosen inputs.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279 · cited 2×
“On the positive side, the concept class being learned is substantially richer than previously achieved, Earlier positive results in learning involve classes whose combinatorial complexity is much more restricted, for example, k-DNF [ 18 ], k-decision lists [15], etc.”
BackgroundMethodHow to construct random functions
Goldreich, O., Goldwasser, S., & Micali, S. (1986) · Journal of the ACM · doi:10.1145/6490.6503 · Cited by 2,115
Theory and application of trapdoor functions
Yao, A. C.-C. (1982) · doi:10.1109/sfcs.1982.95 · Cited by 1,008
Parity, circuits, and the polynomial-time hierarchy
Furst, M., Saxe, J. B., & Sipser, M. (1984) · Mathematical Systems Theory · doi:10.1007/bf01744431 · Cited by 938
Rivest, R. L. (1987) · Machine Learning · doi:10.1007/bf00058680 · Cited by 886
Algebraic methods in the theory of lower bounds for Boolean circuit complexity
Smolensky, R. (1987) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/28395.28404 · Cited by 845
Nisan, N., & Wigderson, A. (1994) · Journal of Computer and System Sciences · doi:10.1016/s0022-0000(05)80043-1 · Cited by 808
Self-citationCryptographic limitations on learning Boolean formulae and finite automata
Kearns, M., & Valiant, L. (1994) · Journal of the ACM · doi:10.1145/174644.174647 · Cited by 733
The influence of variables on Boolean functions
Kahn, J., Kalai, G., & Linial, N. (1988) · [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science · doi:10.1109/sfcs.1988.21923 · Cited by 620
Self-citation∑11-Formulae on finite structures
Ajtai, M. (1983) · Annals of Pure and Applied Logic · doi:10.1016/0168-0072(83)90038-6 · Cited by 585
Cited by
(2006) · The MIT Press eBooks · doi:10.7551/mitpress/9780262033589.001.0001 · Cited by 4,280
(2007) · Cited by 937
O'Donnell, R. (2014) · Cambridge University Press eBooks · doi:10.1017/cbo9781139814782 · Cited by 932
Boolean Functions for Cryptography and Error-Correcting Codes
Carlet, C. (2010) · Boolean Models and Methods in Mathematics, Computer Science, and Engineering · doi:10.1017/cbo9780511780448.011 · Cited by 847
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., & Liao, Q. (2017) · International Journal of Automation and Computing · doi:10.1007/s11633-017-1054-2 · Cited by 559
Oracle-guided component-based program synthesis
Jha, S., Gulwani, S., Seshia, S. A., & Tiwari, A. (2010) · Proceedings of the 32nd ACM/IEEE International Conference on Software Engineering - Volume 1 · doi:10.1145/1806799.1806833 · Cited by 510
Delegating computation: interactive proofs for muggles
Goldwasser, S., Kalai, Y. T., & Rothblum, G. N. (2008) · Proceedings of the fortieth annual ACM symposium on Theory of computing · doi:10.1145/1374376.1374396 · Cited by 484
Derandomizing Polynomial Identity Tests Means Proving Circuit Lower Bounds
Kabanets, V., & Impagliazzo, R. (2004) · computational complexity · doi:10.1007/s00037-004-0182-6 · Cited by 378
Number-theoretic constructions of efficient pseudo-random functions
Naor, M., & Reingold, O. (2004) · Journal of the ACM · doi:10.1145/972639.972643 · Cited by 368
Number-theoretic constructions of efficient pseudo-random functions
Naor, M., & Reingold, O. (2002) · Proceedings 38th Annual Symposium on Foundations of Computer Science · doi:10.1109/sfcs.1997.646134 · Cited by 353
Toward efficient agnostic learning
Kearns, M. J., Schapire, R. E., & Sellie, L. M. (1992) · Proceedings of the fifth annual workshop on Computational learning theory · doi:10.1145/130385.130424 · Cited by 330
Computational learning theory: survey and selected bibliography
Angluin, D. (1992) · Proceedings of the twenty-fourth annual ACM symposium on Theory of computing - STOC '92 · doi:10.1145/129712.129746 · Cited by 316
Near-optimal sparse fourier representations via sampling
Gilbert, A. C., Guha, S., Indyk, P., Muthukrishnan, S., & Strauss, M. (2002) · Proceedings of the thiry-fourth annual ACM symposium on Theory of computing · doi:10.1145/509907.509933 · Cited by 259
Guest Column: A Survey of Quantum Learning Theory
Arunachalam, S., & de Wolf, R. (2017) · ACM SIGACT News · doi:10.1145/3106700.3106710 · Cited by 152
“Classically, the best upper bounds on time complexity of learning AC 0 are quasi-polynomial under the uniform distribution [LMN93], and roughly exp( n 1 / 3 ) in the PAC model (i.e., under all possible distributions) [KS04]; see [DS16] for a recent hardness result.”
Hardness Results for Agnostically Learning Low-Degree Polynomial Threshold Functions
Diakonikolas, I., O'Donnell, R., Servedio, R. A., & Wu, Y. (2011) · Proceedings of the Twenty-Second Annual ACM-SIAM Symposium on Discrete Algorithms · doi:10.1137/1.9781611973082.123 · Cited by 6
Metadata
- Authors
- Linial, N., Mansour, Y., & Nisan, N.
- Venue
- Journal of the ACM
- Published
- 1993-07
- Volume
- 40
- Issue
- 3
- Pages
- 607-620
- ISSN
- 0004-5411 (ISSN-L)
- 1557-735X
- OpenAlex
- W2042194938
- Cited by
- 572
- References
- 17
- FWCI
- 9.03
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.