Sciweavers

76 search results - page 11 / 16
» Agnostically Learning Halfspaces
Sort
View
CORR
2008
Springer
93views Education» more  CORR 2008»
14 years 9 months ago
An optimization problem on the sphere
We prove existence and uniqueness of the minimizer for the average geodesic distance to the points of a geodesically convex set on the sphere. This implies a corresponding existen...
Andreas Maurer
COCO
2010
Springer
149views Algorithms» more  COCO 2010»
15 years 21 days ago
The Gaussian Surface Area and Noise Sensitivity of Degree-d Polynomial Threshold Functions
Abstract. We prove asymptotically optimal bounds on the Gaussian noise sensitivity of degree-d polynomial threshold functions. These bounds translate into optimal bounds on the Gau...
Daniel M. Kane
COLT
1995
Springer
15 years 1 months ago
Learning with Unreliable Boundary Queries
We introduce a new model for learning with membership queries in which queries near the boundary of a target concept may receive incorrect or “don’t care” responses. In part...
Avrim Blum, Prasad Chalasani, Sally A. Goldman, Do...
FOCS
2010
IEEE
14 years 7 months ago
Learning Convex Concepts from Gaussian Distributions with PCA
We present a new algorithm for learning a convex set in n-dimensional space given labeled examples drawn from any Gaussian distribution. The complexity of the algorithm is bounded ...
Santosh Vempala
ICML
2004
IEEE
15 years 10 months ago
Online and batch learning of pseudo-metrics
We describe and analyze an online algorithm for supervised learning of pseudo-metrics. The algorithm receives pairs of instances and predicts their similarity according to a pseud...
Shai Shalev-Shwartz, Yoram Singer, Andrew Y. Ng