Sciweavers

181 search results - page 21 / 37
» Polynomial Learning of Distribution Families
Sort
View
JMLR
2010
134views more  JMLR 2010»
13 years 4 months ago
Using Contextual Representations to Efficiently Learn Context-Free Languages
We present a polynomial update time algorithm for the inductive inference of a large class of context-free languages using the paradigm of positive data and a membership oracle. W...
Alexander Clark, Rémi Eyraud, Amaury Habrar...
COLT
2006
Springer
14 years 1 months ago
Efficient Learning Algorithms Yield Circuit Lower Bounds
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
Lance Fortnow, Adam R. Klivans
ICS
2010
Tsinghua U.
14 years 1 months ago
Weight Distribution and List-Decoding Size of Reed-Muller Codes
: We study the weight distribution and list-decoding size of Reed-Muller codes. Given a weight parameter, we are interested in bounding the number of Reed-Muller codewords with a w...
Tali Kaufman, Shachar Lovett, Ely Porat
EUROCOLT
1999
Springer
14 years 2 months ago
Query by Committee, Linear Separation and Random Walks
Abstract. Recent works have shown the advantage of using Active Learning methods, such as the Query by Committee (QBC) algorithm, to various learning problems. This class of Algori...
Ran Bachrach, Shai Fine, Eli Shamir
JMLR
2006
186views more  JMLR 2006»
13 years 9 months ago
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
Mikhail Belkin, Partha Niyogi, Vikas Sindhwani