Learning polynomials with queries: The highly noisy case

Given a function f mappping n-variate inputs from a finite field F into F, we consider the task of reconstructing a list of all n-variate degree d polynomials which agree with f on a tiny but non-negligible fraction, /spl delta/, of the input space. We give a randomized algorithm for solving this task which accesses f as a black box and runs in time polynomial in 1//spl delta/, n and exponential in d, provided /spl delta/ is /spl Omega/(/spl radic/(d.

[1]  Ronitt Rubinfeld,et al.  On the learnability of discrete distributions , 1994, STOC '94.

[2]  Oded Goldreich,et al.  Foundations of Cryptography (Fragments of a Book) , 1995 .

[3]  Vijay V. Vazirani,et al.  Efficient and Secure Pseudo-Random Number Generation (Extended Abstract) , 1984, FOCS.

[4]  Ronitt Rubinfeld,et al.  Robust Characterizations of Polynomials with Applications to Program Testing , 1996, SIAM J. Comput..

[5]  Richard Zippel Effective polynomial computation , 1993, The Kluwer international series in engineering and computer science.

[6]  P. Laird Learning from Good and Bad Data , 1988 .

[7]  Yishay Mansour,et al.  Randomized Interpolation and Approximation of Sparse Polynomials , 1992, SIAM J. Comput..

[8]  Dana Ron,et al.  Learning to model sequences generated by switching distributions , 1995, COLT '95.

[9]  Madhu Sudan,et al.  Improved low-degree testing and its applications , 1997, STOC '97.

[10]  Richard Zippel Interpolating Polynomials from Their Values , 1990, J. Symb. Comput..

[11]  M. Kearns On the Learnability of Discrete Distributions Extended Abstract , 1994 .

[12]  Robert E. Schapire,et al.  Exact Identification of Read-Once Formulas Using Fixed Points of Amplification Functions , 1993, SIAM J. Comput..

[13]  Jacob T. Schwartz,et al.  Fast Probabilistic Algorithms for Verification of Polynomial Identities , 1980, J. ACM.

[14]  Wolfgang Maass Efficient agnostic PAC-learning with simple hypothesis , 1994, COLT '94.

[15]  Richard J. Lipton,et al.  Cryptographic Primitives Based on Hard Learning Problems , 1993, CRYPTO.

[16]  Pascal Koiran Efficient learning of continuous neural networks , 1994, COLT '94.

[17]  Richard J. Lipton,et al.  A Probabilistic Remark on Algebraic Program Testing , 1978, Inf. Process. Lett..

[18]  Madhu Sudan,et al.  Highly Resilient Correctors for Polynomials , 1992, Inf. Process. Lett..

[19]  Robert H. Sloan,et al.  Corrigendum to types of noise in data for concept learning , 1988, COLT '92.

[20]  Michael Kearns,et al.  Efficient noise-tolerant learning from statistical queries , 1993, STOC '93.

[21]  R. Schapire,et al.  Toward Efficient Agnostic Learning , 1994 .

[22]  FunctionsSally,et al.  Exact Identi cation of Read-once Formulas Using Fixed Points ofAmpli cation , 1992 .

[23]  Ming Li,et al.  Learning in the presence of malicious errors , 1988, STOC '88.

[24]  MaassWolfgang Agnostic PAC learning of functions on analog neural nets , 1995 .

[25]  Rani Siromoney,et al.  A noise model on learning sets of strings , 1992, COLT '92.

[26]  Ronitt Rubinfeld,et al.  Reconstructing algebraic functions from mixed data , 1992, Proceedings., 33rd Annual Symposium on Foundations of Computer Science.

[27]  Yasubumi Sakakibara On Learning from Queries and Counterexamples in the Presence of Noise , 1991, Inf. Process. Lett..

[28]  Madhu Sudan Decoding of Reed Solomon Codes beyond the Error-Correction Bound , 1997, J. Complex..

[29]  O. Antoine,et al.  Theory of Error-correcting Codes , .

[30]  Manuel Blum,et al.  Self-testing/correcting with applications to numerical problems , 1990, STOC '90.

[31]  Joan Feigenbaum,et al.  Hiding Instances in Multioracle Queries , 1990, STACS.

[32]  Eyal Kushilevitz,et al.  Learning decision trees using the Fourier spectrum , 1991, STOC '91.

[33]  Ronitt Rubinfeld,et al.  Learning fallible finite state automata , 1993, COLT '93.

[34]  Vijay V. Vazirani,et al.  Efficient and Secure Pseudo-Random Number Generation , 1984, CRYPTO.

[35]  M. Sudan,et al.  Robust Characterizations of Polynomials and Their Applications to Program Testing , 1993 .

[36]  Ronitt Rubinfeld,et al.  Self-testing/correcting for polynomials and for approximate functions , 1991, STOC '91.

[37]  Peter Elias,et al.  List decoding for noisy channels , 1957 .

[38]  Leonid A. Levin,et al.  A hard-core predicate for all one-way functions , 1989, STOC '89.

[39]  Linda Sellie,et al.  Toward efficient agnostic learning , 1992, COLT '92.

[40]  Wolfgang Maass,et al.  Agnostic PAC Learning of Functions on Analog Neural Nets , 1993, Neural Computation.

[41]  Dana Angluin,et al.  Learning with malicious membership queries and exceptions (extended abstract) , 1994, COLT '94.

[42]  Richard J. Lipton,et al.  New Directions In Testing , 1989, Distributed Computing And Cryptography.

[43]  Avrim Blum,et al.  Learning switching concepts , 1992, COLT '92.

[44]  Richard Zippel,et al.  Probabilistic algorithms for sparse polynomials , 1979, EUROSAM.

[45]  Philip D. Laird,et al.  Learning from good data and bad , 1987 .