Matches in SemOpenAlex for { <https://semopenalex.org/work/W2308457303> ?p ?o ?g. }
- W2308457303 abstract "This thesis explores problems in computational learning theory from an average-case perspective. Through this perspective we obtain a variety of new results for learning theory and cryptography. Several major open questions in computational learning theory revolve around the problem of efficiently learning polynomial-size DNF formulas, which dates back to Valiant's introduction of the PAC learning model [Valiant, 1984]. We apply an average-case analysis to make progress on this problem in two ways. (1) We prove that Mansour's conjecture is true for random DNF. In 1994, Y. Mansour conjectured that for every DNF formula on n variables with t terms there exists a polynomial p with tO(log(1/e)) non-zero coefficients such that Ex∈0,1 n [(p(x) − f( x))2] ≤ e. We make the first progress on this conjecture and show that it is true for several natural subclasses of DNF formulas including randomly chosen DNF formulas and read-k DNF formulas. Our result yields the first polynomial-time query algorithm for agnostically learning these subclasses of DNF formulas with respect to the uniform distribution on {0, 1}n (for any constant error parameter and constant k). Applying recent work on sandwiching polynomials, our results imply that t −O(log 1/e)-biased distributions fool the above subclasses of DNF formulas. This gives pseudorandom generators for these subclasses with shorter seed length than all previous work. (2) We give an efficient algortihm that learns random monotone DNF. The problem of efficiently learning the monotone subclass of polynomial-size DNF formulas from random examples was also posed in [Valiant, 1984]. This notoriously difficult question is still open, despite much study and the fact that known impediments to learning the non-monotone class (cf. [Blum et al., 1994; Blum, 2003a]) do not exist for monotone DNF formulas. We give the first algorithm that learns randomly chosen monotone DNF formulas of arbitrary polynomial size, improving results which efficiently learn n2−e-size random monotone DNF formulas [Jackson and Servedio, 2005b]. Our main structural result is that most monotone DNF formulas reveal their term structure in their constant-degree Fourier coefficients. In this thesis, we also see that connections between learning and cryptography are naturally made through average-case analysis. First, by applying techniques from average-case complexity, we demonstrate new ways of using cryptographic assumptions to prove limitations on learning. As counterpoint, we also exploit the average-case connection in the service of cryptography. Below is a more detailed description of these contributions. (1) We show that monotone polynomial-sized circuits are hard to learn if one-way functions exist. We establish the first cryptographic hardness results for learning polynomial-size classes of monotone circuits, giving a computational analogue of the information-theoretic hardness results of [Blum et al., 1998]. Some of our results show the cryptographic hardness of learning polynomial-size monotone circuits to accuracy only slightly greater than 1/2 + 1/ n ; this is close to the optimal accuracy bound, by positive results of Blum, et al. Our main tool is a complexity-theoretic approach to hardness amplification vianoise sensitivity of monotone functions that was pioneered by O'Donnell [O'Donnell, 2004a]. (2) Learning an overcomplete basis: analysis of lattice-based signatures with perturbations. Lattice-based cryptographic constructions are desirable not only because they provide security based on worst-case hardness assumptions, but also because they can be extremely efficient and practical. We propose a general technique for recovering parts of the secret key in lattice-based signature schemes that follow the Goldreich-Goldwasser-Halevi (GGH) and NTRUSign design with perturbations. Our technique is based on solving a learning problem in the average-case. To solve the average-case problem, we propose a special-purpose optimization algorithm based on higher-order cumulants of the signature distribution, and give theoretical and experimental evidence of its efficacy. Our results suggest (but do not conclusively prove) that NTRUSign is vulnerable to a polynomial-time attack." @default.
- W2308457303 created "2016-06-24" @default.
- W2308457303 creator A5014866889 @default.
- W2308457303 creator A5052376364 @default.
- W2308457303 creator A5058081649 @default.
- W2308457303 date "2010-01-01" @default.
- W2308457303 modified "2023-09-24" @default.
- W2308457303 title "Learning, cryptography, and the average case" @default.
- W2308457303 cites W129174014 @default.
- W2308457303 cites W129929154 @default.
- W2308457303 cites W1489617931 @default.
- W2308457303 cites W149470655 @default.
- W2308457303 cites W1507505284 @default.
- W2308457303 cites W1520252399 @default.
- W2308457303 cites W1529556207 @default.
- W2308457303 cites W1548802052 @default.
- W2308457303 cites W1551509424 @default.
- W2308457303 cites W1569556792 @default.
- W2308457303 cites W1601111578 @default.
- W2308457303 cites W1606064697 @default.
- W2308457303 cites W1675339804 @default.
- W2308457303 cites W1784600267 @default.
- W2308457303 cites W184459354 @default.
- W2308457303 cites W1856342626 @default.
- W2308457303 cites W1893972099 @default.
- W2308457303 cites W1899006432 @default.
- W2308457303 cites W1982381767 @default.
- W2308457303 cites W1992226551 @default.
- W2308457303 cites W1996160381 @default.
- W2308457303 cites W2002901911 @default.
- W2308457303 cites W2011618217 @default.
- W2308457303 cites W2011717937 @default.
- W2308457303 cites W2015880590 @default.
- W2308457303 cites W2017290750 @default.
- W2308457303 cites W2019363670 @default.
- W2308457303 cites W2019807548 @default.
- W2308457303 cites W2021736779 @default.
- W2308457303 cites W2023691706 @default.
- W2308457303 cites W2026103826 @default.
- W2308457303 cites W2029286977 @default.
- W2308457303 cites W2029370139 @default.
- W2308457303 cites W2029948740 @default.
- W2308457303 cites W2033049828 @default.
- W2308457303 cites W2038761522 @default.
- W2308457303 cites W2042194938 @default.
- W2308457303 cites W2043629999 @default.
- W2308457303 cites W2043842763 @default.
- W2308457303 cites W2046054273 @default.
- W2308457303 cites W2047430378 @default.
- W2308457303 cites W2048284438 @default.
- W2308457303 cites W2062965695 @default.
- W2308457303 cites W2063003848 @default.
- W2308457303 cites W2064680241 @default.
- W2308457303 cites W2069191912 @default.
- W2308457303 cites W2070540961 @default.
- W2308457303 cites W2074734756 @default.
- W2308457303 cites W2074876220 @default.
- W2308457303 cites W2076458424 @default.
- W2308457303 cites W2079520411 @default.
- W2308457303 cites W2079866219 @default.
- W2308457303 cites W2081192873 @default.
- W2308457303 cites W2081256580 @default.
- W2308457303 cites W2082175413 @default.
- W2308457303 cites W2088390444 @default.
- W2308457303 cites W2088559598 @default.
- W2308457303 cites W2094660504 @default.
- W2308457303 cites W2095546965 @default.
- W2308457303 cites W2096295738 @default.
- W2308457303 cites W2100008268 @default.
- W2308457303 cites W2100654536 @default.
- W2308457303 cites W2103749128 @default.
- W2308457303 cites W2106458073 @default.
- W2308457303 cites W2110503949 @default.
- W2308457303 cites W2111416661 @default.
- W2308457303 cites W2112556578 @default.
- W2308457303 cites W2117362057 @default.
- W2308457303 cites W2119219964 @default.
- W2308457303 cites W2119243017 @default.
- W2308457303 cites W2124218043 @default.
- W2308457303 cites W2124619161 @default.
- W2308457303 cites W2124646923 @default.
- W2308457303 cites W2126546664 @default.
- W2308457303 cites W2131866098 @default.
- W2308457303 cites W2138036903 @default.
- W2308457303 cites W2144579822 @default.
- W2308457303 cites W2146908714 @default.
- W2308457303 cites W2147306258 @default.
- W2308457303 cites W2149840272 @default.
- W2308457303 cites W2152772468 @default.
- W2308457303 cites W2157754126 @default.
- W2308457303 cites W2160403361 @default.
- W2308457303 cites W2161714146 @default.
- W2308457303 cites W2168115971 @default.
- W2308457303 cites W2173249896 @default.
- W2308457303 cites W2245160765 @default.
- W2308457303 cites W2295428206 @default.
- W2308457303 cites W2397273652 @default.
- W2308457303 cites W2408026461 @default.
- W2308457303 cites W2584956713 @default.
- W2308457303 cites W2885803187 @default.