Results 1  10
of
1,034,638
Active learning in the nonrealizable case
 NIPS Workshop on Foundations of Active Learning
, 2006
"... Abstract. Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly classifies all training and test examples. This assumption can hardly ever be justified in practice. In this pape ..."
Abstract

Cited by 50 (0 self)
 Add to MetaCart
shows that if we move to the truly nonrealizable model of statistical learning theory, then the label complexity of active learning has the same dependence Ω(1/ǫ 2) on the accuracy parameter ǫ as the passive learning label complexity. More specifically, we show that under the assumption that the best
Multiview active learning in the nonrealizable case
 In Advances in Neural Information Processing Systems
"... The sample complexity of active learning under the realizability assumption has been wellstudied. The realizability assumption, however, rarely holds in practice. In this paper, we theoretically characterize the sample complexity of active learning in the nonrealizable case under multiview setti ..."
Abstract

Cited by 7 (4 self)
 Add to MetaCart
The sample complexity of active learning under the realizability assumption has been wellstudied. The realizability assumption, however, rarely holds in practice. In this paper, we theoretically characterize the sample complexity of active learning in the nonrealizable case under multi
Sequence prediction in realizable and nonrealizable cases
"... A sequence x1,..., xn,... of discretevalued observations is generated according to some unknown probabilistic law (measure) µ. After observing each outcome, it is required to give the conditional probabilities of the next observation. The realizable case is when the measure µ belongs to an arbitrar ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
show that when a solution exists, it can be obtained as a Bayes mixture over a countable subset of C. As an illustration to the general results obtained, we show that a solution to the nonrealizable case of the sequence prediction problem exists for the set of all finitememory processes, but does
Online passiveaggressive algorithms
 JMLR
, 2006
"... We present a unified view for online classification, regression, and uniclass problems. This view leads to a single algorithmic framework for the three problems. We prove worst case loss bounds for various algorithms for both the realizable case and the nonrealizable case. The end result is new alg ..."
Abstract

Cited by 420 (24 self)
 Add to MetaCart
We present a unified view for online classification, regression, and uniclass problems. This view leads to a single algorithmic framework for the three problems. We prove worst case loss bounds for various algorithms for both the realizable case and the nonrealizable case. The end result is new
On the Relation between Realizable and Nonrealizable Cases of the Sequence Prediction Problem
"... A sequence x1,...,xn,... of discretevalued observations is generated according to some unknown probabilistic law (measure) µ. After observing each outcome, one is required to give conditional probabilities of the next observation. The realizable case is when the measure µ belongs to an arbitrary bu ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
but known class C of process measures. The nonrealizable case is when µ is completely arbitrary, but the prediction performance is measured with respect to a given setC of process measures. We are interested in the relations between these problems and between their solutions, as well as in characterizing
ON THE NONREALIZABILITY OF BRAID GROUPS BY DIFFEOMORPHISMS
"... Abstract. For every compact surface S of finite type (possibly with boundary components but without punctures), we show that when n is sufficiently large there is no lift σ of the surface braid group Bn(S) to Diff(S, n), the group of diffeomorphisms preserving n marked points and restricting to the ..."
Abstract
 Add to MetaCart
to the identity on the boundary. Our methods are applied to give a new proof of Morita’s nonlifting theorem in the best possible range. These techniques extend to the more general setting of spaces of codimension2 embeddings, and we obtain corresponding results for spherical motion groups, including the string
The case for motivated reasoning
 Psychological Bulletin
, 1990
"... It is proposed that motivation may affect reasoning through reliance on a biased set of cognitive processes—that is, strategies for accessing, constructing, and evaluating beliefs. The motivation to be accurate enhances use of those beliefs and strategies that are considered most appropriate, wherea ..."
Abstract

Cited by 687 (3 self)
 Add to MetaCart
It is proposed that motivation may affect reasoning through reliance on a biased set of cognitive processes—that is, strategies for accessing, constructing, and evaluating beliefs. The motivation to be accurate enhances use of those beliefs and strategies that are considered most appropriate, whereas the motivation to arrive at particular conclusions enhances use of those that are considered most likely to yield the desired conclusion. There is considerable evidence that people are more likely to arrive at conclusions that they want to arrive at, but their ability to do so is constrained by their ability to construct seemingly reasonable justifications for these conclusions. These ideas can account for a wide variety of research concerned with motivated reasoning. The notion that goals or motives affect reasoning has a long and controversial history in social psychology. The propositions that motives may affect perceptions (Erdelyi, 1974), attitudes (Festinger, 1957), and attributions (Heider, 1958) have been put forth by some psychologists and challenged by others. Although early researchers and theorists took it for granted that motivation may cause people to make selfserving attributions
TransformationBased ErrorDriven Learning and Natural Language Processing: A Case Study in PartofSpeech Tagging
 Computational Linguistics
, 1995
"... this paper, we will describe a simple rulebased approach to automated learning of linguistic knowledge. This approach has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance. We present a detailed case study of this learni ..."
Abstract

Cited by 916 (7 self)
 Add to MetaCart
this paper, we will describe a simple rulebased approach to automated learning of linguistic knowledge. This approach has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance. We present a detailed case study
Nonrealizability and ending lamination  Proof of the Density Conjecture
, 2010
"... We give a complete proof of the BersSullivanThurston Density Conjecture. In the light of the Ending lamination theorem, it suffices to prove that any collection of possible ending invariants is realized by some algebraic limit of geometrically finite hyperbolic manifolds. The ending invariants a ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
of the filling laminations is realized by a pleated surface. In order to be able to apply the Ending Lamination Theorem we have to prove that this algebraic limit has the desired topological type and that these nonrealized laminations are ending laminations. That this is the case is the main novel technical
Results 1  10
of
1,034,638