Results 1  10
of
6,806
Biimmunity Results for Cheatable Sets
 Theoretical Computer Science
, 1995
"... An oracle A is kcheatable if there is a polynomialtime algorithm to determine the answers to 2 k parallel queries to A from the answers to only k queries to some other oracle B. It is known that 1cheatable sets cannot be biimmune for P. In contrast, we construct 2cheatable sets that are biim ..."
Abstract

Cited by 10 (6 self)
 Add to MetaCart
for arbitrary time complexity classes. In addition, for each k, we construct a set that is (k + 1)cheatable, but not kcheatable; we show that this separation does not hold with biimmunity. We show that if a recursive set A is biimmune for P then there exists an infinite 1cheatable set that is polynomial
A Note on Genericity and BiImmunity
 In Proceedings of the Tenth Annual Structure in Complexity Theory Conference
, 1995
"... Generic sets have all properties (from among a suitably chosen class) that can be enforced by finite extension arguments. In particular, pgeneric sets are known to be Pbiimmune. We try to clarify the precise relationship between genericity and biimmunity by proposing an extended notion of biimm ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
Generic sets have all properties (from among a suitably chosen class) that can be enforced by finite extension arguments. In particular, pgeneric sets are known to be Pbiimmune. We try to clarify the precise relationship between genericity and biimmunity by proposing an extended notion of biimmunity
Quantum complexity theory
 in Proc. 25th Annual ACM Symposium on Theory of Computing, ACM
, 1993
"... Abstract. In this paper we study quantum computation from a complexity theoretic viewpoint. Our first result is the existence of an efficient universal quantum Turing machine in Deutsch’s model of a quantum Turing machine (QTM) [Proc. Roy. Soc. London Ser. A, 400 (1985), pp. 97–117]. This constructi ..."
Abstract

Cited by 574 (5 self)
 Add to MetaCart
the modern (complexity theoretic) formulation of the Church–Turing thesis. We show the existence of a problem, relative to an oracle, that can be solved in polynomial time on a quantum Turing machine, but requires superpolynomial time on a boundederror probabilistic Turing machine, and thus not in the class
Optimal Brain Damage
, 1990
"... We have used informationtheoretic ideas to derive a class of practical and nearly optimal schemes for adapting the size of a neural network. By removing unimportant weights from a network, several improvements can be expected: better generalization, fewer training examples required, and improved sp ..."
Abstract

Cited by 510 (5 self)
 Add to MetaCart
speed of learning and/or classification. The basic idea is to use secondderivative information to make a tradeoff between network complexity and training set error. Experiments confirm the usefulness of the methods on a realworld application.
Interiorpoint Methods
, 2000
"... The modern era of interiorpoint methods dates to 1984, when Karmarkar proposed his algorithm for linear programming. In the years since then, algorithms and software for linear programming have become quite sophisticated, while extensions to more general classes of problems, such as convex quadrati ..."
Abstract

Cited by 612 (15 self)
 Add to MetaCart
The modern era of interiorpoint methods dates to 1984, when Karmarkar proposed his algorithm for linear programming. In the years since then, algorithms and software for linear programming have become quite sophisticated, while extensions to more general classes of problems, such as convex
A Theory of the Learnable
, 1984
"... Humans appear to be able to learn new concepts without needing to be programmed explicitly in any conventional sense. In this paper we regard learning as the phenomenon of knowledge acquisition in the absence of explicit programming. We give a precise methodology for studying this phenomenon from ..."
Abstract

Cited by 1985 (15 self)
 Add to MetaCart
a computational viewpoint. It consists of choosing an appropriate information gathering mechanism, the learning protocol, and exploring the class of concepts that can be learnt using it in a reasonable (polynomial) number of steps. We find that inherent algorithmic complexity appears to set serious
Large margin methods for structured and interdependent output variables
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2005
"... Learning general functional dependencies between arbitrary input and output spaces is one of the key challenges in computational intelligence. While recent progress in machine learning has mainly focused on designing flexible and powerful input representations, this paper addresses the complementary ..."
Abstract

Cited by 624 (12 self)
 Add to MetaCart
the complementary issue of designing classification algorithms that can deal with more complex outputs, such as trees, sequences, or sets. More generally, we consider problems involving multiple dependent output variables, structured output spaces, and classification problems with class attributes. In order
The strength of weak learnability
 MACHINE LEARNING
, 1990
"... This paper addresses the problem of improving the accuracy of an hypothesis output by a learning algorithm in the distributionfree (PAC) learning model. A concept class is learnable (or strongly learnable) if, given access to a Source of examples of the unknown concept, the learner with high prob ..."
Abstract

Cited by 871 (26 self)
 Add to MetaCart
, the construction has some interesting theoretical consequences, including a set of general upper bounds on the complexity of any strong learning algorithm as a function of the allowed error e.
Amortized Efficiency of List Update and Paging Rules
, 1985
"... In this article we study the amortized efficiency of the “movetofront” and similar rules for dynamically maintaining a linear list. Under the assumption that accessing the ith element from the front of the list takes 0(i) time, we show that movetofront is within a constant factor of optimum amo ..."
Abstract

Cited by 824 (8 self)
 Add to MetaCart
paging, a setting in which the access cost is not convex. The paging rule corresponding to movetofront is the “least recently used” (LRU) replacement rule. We analyze the amortized complexity of LRU, showing that its efficiency differs from that of the offline paging rule (Belady’s MIN algorithm) by a
Probabilistic Inference Using Markov Chain Monte Carlo Methods
, 1993
"... Probabilistic inference is an attractive approach to uncertain reasoning and empirical learning in artificial intelligence. Computational difficulties arise, however, because probabilistic models with the necessary realism and flexibility lead to complex distributions over highdimensional spaces. R ..."
Abstract

Cited by 736 (24 self)
 Add to MetaCart
Probabilistic inference is an attractive approach to uncertain reasoning and empirical learning in artificial intelligence. Computational difficulties arise, however, because probabilistic models with the necessary realism and flexibility lead to complex distributions over highdimensional spaces
Results 1  10
of
6,806