{"title":"The complexity of learning with queries","authors":"Ricard Gavaldà","doi":"10.1109/SCT.1994.315791","DOIUrl":"https://doi.org/10.1109/SCT.1994.315791","url":null,"abstract":"We survey recent research concerning the qualitative complexity of Angluin's (1993) model of learning with queries. In this model, there is a learner that tries to identify a target concept by means of queries to a teacher. Thus, the process can be naturally formulated as an oracle computation. Among the results we review there are: characterizations of the power of different learning protocols by complexity classes of oracle machines; relations between the complexity of learning and the complexity of computing advice functions for nonuniform classes; and combinatorial characterizations of the concept classes that are learnable in specific protocols.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115623823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Predicate classes and promise classes","authors":"Bernd Borchert","doi":"10.1109/SCT.1994.315800","DOIUrl":"https://doi.org/10.1109/SCT.1994.315800","url":null,"abstract":"Considering computation trees produced by polynomial time nondeterministic computations one can define a complexity class by any predicate on computation trees, such classes will be called predicate classes. It will be shown that these classes are exactly the principal ideals of the polynomial time many-one reducibility. Additionally, the set of classes-which are called promise classes-definable by promise functions instead of predicates are shown to be equal to the set of countable ideals.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127671986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Weakly hard problems","authors":"J. H. Lutz","doi":"10.1109/SCT.1994.315808","DOIUrl":"https://doi.org/10.1109/SCT.1994.315808","url":null,"abstract":"A weak completeness phenomenon is investigated in the complexity class E=DTIME(2/sup linear/). According to standard terminology, a language H is /spl lessub msup P/-hard for E if the set P/sub m/(H), consisting of all languages A/spl lessub msup P/H, contains the entire class E. A language C is /spl lessub msup P/-complete for E if it is /spl lessub msup P/-hard for E and is also an element of E. Generalizing this, a language H is weakly /spl lessub msup P/-hard for E if the set P/sub m/(H) does not have measure 0 in E. A language C is weakly /spl lessub msup P/-complete for E if it is weakly /spl lessub msup P/-hard for E and is also an element of E. The main result of this paper is the construction of a language that is weakly /spl lessub msup P/-complete, but not /spl lessub msup P/-complete, for E. The existence of such languages implies that previously known strong lower bounds on the complexity of weakly /spl lessub msup P/-hard problems for E are indeed more general than the corresponding bounds for /spl lessub msup P/-hard problems for E. The proof of this result introduces a new diagonalization method, called martingale diagonalization. Using this method, one simultaneously develops an infinite family of polynomial time computable martingales (betting strategies) and a corresponding family of languages that defeat these martingales (i.e. prevent them from winning too much money), while also pursuing another agenda. Martingale diagonalization may be useful for a variety of applications.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128590517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Relative to a random oracle, NP is not small","authors":"Steven M. Kautz, Peter Bro Miltersen","doi":"10.1109/SCT.1994.315807","DOIUrl":"https://doi.org/10.1109/SCT.1994.315807","url":null,"abstract":"The resource-bounded measure (J. Lutz, 1992) is an extension of classical measure theory which provides a probabilistic means of describing the relative sizes of complexity classes. Lutz proposed the hypothesis that NP does not have measure zero in the class E/sub 2/=DTIME(2/sup polynomial/), meaning loosely that NP contains a non-negligible subset of exponential time. This hypothesis implies a strong separation of P from NP and is supported by a growing body of plausible consequences which are not known to follow from the weaker assertion P/spl ne/NP. It is shown that relative to a random oracle, NP does not have measure zero in E/sub 2/, improving the result of Bennett and Gill (1981) that P/spl ne/NP relative to a random oracle. Several new techniques are introduced; in particular the proof exploits the independence properties of algorithmically random sequences, and a strong independence result is shown: if A is an algorithmically random sequence and a subsequence A/sub 0/ is chosen by means of a bounded Kolmogorov-Loveland place selection, then the sequence A/sub 1/ of unselected bits is random relative to A/sub 0/, i.e. A/sub 0/ and A/sub 1/ are independent. A bounded Kolmogorov-Loveland place selection is a very general type of recursive selection rule which may be interpreted as the sequence of oracle queries of a time-bounded Turing machine, so the methods used may be applicable to other questions involving random oracles.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125986975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Complexity classes defined via k-valued functions","authors":"U. Hertrampf","doi":"10.1109/SCT.1994.315801","DOIUrl":"https://doi.org/10.1109/SCT.1994.315801","url":null,"abstract":"A lot of complexity classes can be characterized by posing some global acceptance condition on the computation trees produced by nondeterministic polynomial time machines. If the acceptance condition can be performed by a tree automaton, we obtain the concept of locally definable acceptance types (U. Hertrampf, 1992). This concept can be varied in different ways: if the acceptance condition depends only on the leaves of the computation tree, we obtain the concept of leaf languages (D. Bovet et al., 1991); if moreover the leaf language has to be a regular set, we obtain associative acceptance types. A special case appears, if we just count the number /spl alpha/ of accepting paths up to a fixed maximal value c (i.e. /spl alpha/=max(# accepting paths, c)) and then check, whether /spl alpha/ belongs to a given subset A/spl sube/{0,...,c-1}. This concept leads to complexity classes with finite acceptance types. We survey all these concepts and compare their power.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122723230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Random debaters and the hardness of approximating stochastic functions","authors":"A. Condon, J. Feigenbaum, C. Lund, P. Shor","doi":"10.1109/SCT.1994.315796","DOIUrl":"https://doi.org/10.1109/SCT.1994.315796","url":null,"abstract":"A random probabilistically checkable debate system (RPCDS) for a language L consists of a probabilistic polynomial-time verifier V and a debate between Player 1, who aims to prove that the input x is in L, and Player 0, who selects a move uniformly at random from the set of legal moves. This model is a natural restriction of the PCDS model (Condon et al., Proc. 25th ACM Symposium on Theory of Computing, p.304-15, 1993,). We show that L has an RPCDS in which the verifier flips O(log n) coins and reads O(1) bits of the debate if and only if L is in PSPACE. Using this new characterization of PSPACE, we show that certain stochastic PSPACE-hard functions are as hard to approximate closely as they are to compute exactly. Examples include optimization versions of dynamic graph reliability, stochastic satisfiability, Mah-Jongg, stochastic coloring, stochastic generalized geography, and other \"games against nature\".<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132679298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Downward separation fails catastrophically for limited nondeterminism classes","authors":"R. Beigel, J. Goldsmith","doi":"10.1109/SCT.1994.315810","DOIUrl":"https://doi.org/10.1109/SCT.1994.315810","url":null,"abstract":"The /spl beta/ hierarchy consists of sets /spl betasub k/=NP[log/sup k/ n]/spl sube/NP. Unlike collapses in the polynomial hierarchy and the Boolean hierarchy, collapses in the /spl beta/ hierarchy do not seem to translate up, nor does closure under complement seem to cause the hierarchy to collapse. For any consistent set of collapses and separations of levels of the hierarchy that respects P=/spl betasub 1spl subespl betasub 2spl sube/.../spl sube/NP, we can construct an oracle relative to which those collapses and separations hold, yet any (or all) of the /spl betasub k/'s are closed under complement. We give a few relatively tame examples: first, for any k/spl ges/1, we construct an oracle relative to which P=/spl betasub kspl nespl betasub k+1spl nespl betasub k+2spl ne/..., and then another oracle relative to which P=/spl betasub kspl nespl betasub k+1/=PSPACE. We also construct an oracle relative to which /spl betasub 2k/=/spl betasub 2k+1spl nespl betasub 2k+2/ for all k. These results hold for more general nondeterminism hierarchies within NP, although they are in sharp contrast to the upward collapse results for Buss and Goldsmith's (1993) nondeterminism hierarchy in P.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133112739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Complexity theory and genetics","authors":"P. Pudlák","doi":"10.1109/SCT.1994.315787","DOIUrl":"https://doi.org/10.1109/SCT.1994.315787","url":null,"abstract":"We introduce a population genetics model in which the operators are effectively computable-computable in polynomial time on probabilistic Turing machines. We shall show that in this model a population can encode easily large amount of information from environment into genetic code. Then it can process the information as a parallel computer. More precisely, we show that it can stimulate polynomial space computations in polynomially many steps, even if the recombination rules are very simple.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124360613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Time, hardware, and uniformity","authors":"D. M. Barrington, N. Immerman","doi":"10.1109/SCT.1994.315806","DOIUrl":"https://doi.org/10.1109/SCT.1994.315806","url":null,"abstract":"We describe three orthogonal complexity measures: parallel time, amount of hardware, and degree of non-uniformity, which together parametrize most complexity classes. We show that the descriptive complexity framework neatly captures these measures using the parameters: quantifier depth, number of variable bits, and type of numeric predicates respectively. A fairly simple picture arises in which the basic questions in complexity theory-solved and unsolved-can be understood as questions about tradeoffs among these three dimensions.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123186614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Unambiguous polynomial hierarchies and exponential size","authors":"Klaus-Jörn Lange, P. Rossmanith","doi":"10.1109/SCT.1994.315812","DOIUrl":"https://doi.org/10.1109/SCT.1994.315812","url":null,"abstract":"The classes NC/sup k/ and AC/sup k/ are defined by computational devices of polynomial size, i.e. by devices using a polynomially bounded number of gates or processors. We consider the case of exponential size, which results in classes between P and PSPACE. In this way, we get new characterizations of P and UP. The resulting relations of nondeterminism, unambiguity, and determinism to several types of simultaneous write access to a shared memory perfectly resemble the polynomial case. A new phenomenon is the equivalence of concurrent read, exclusive read, and owner read for arbitrary types of write access in the case of exponential size. In the exponential case, circuits of bounded depth characterize the polynomial hierarchy. Using the notion of an unambiguous circuit, we give a uniform framework to relate the various types of unambiguous polynomial hierarchies and to explain their differences.<<ETX>>","PeriodicalId":386782,"journal":{"name":"Proceedings of IEEE 9th Annual Conference on Structure in Complexity Theory","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124765299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}