Sciweavers

3934 search results - page 499 / 787
» Approximate Schedulability Analysis
Sort
View
JMLR
2008
88views more  JMLR 2008»
15 years 6 months ago
Universal Multi-Task Kernels
In this paper we are concerned with reproducing kernel Hilbert spaces HK of functions from an input space into a Hilbert space Y, an environment appropriate for multi-task learnin...
Andrea Caponnetto, Charles A. Micchelli, Massimili...
ML
2008
ACM
15 years 6 months ago
A bias/variance decomposition for models using collective inference
Bias/variance analysis is a useful tool for investigating the performance of machine learning algorithms. Conventional analysis decomposes loss into errors due to aspects of the le...
Jennifer Neville, David Jensen
FOCS
2010
IEEE
15 years 4 months ago
The Limits of Two-Party Differential Privacy
We study differential privacy in a distributed setting where two parties would like to perform analysis of their joint data while preserving privacy for both datasets. Our results ...
Andrew McGregor, Ilya Mironov, Toniann Pitassi, Om...
ICDAR
2011
IEEE
14 years 6 months ago
Word Retrieval in Historical Document Using Character-Primitives
Word searching and indexing in historical document collections is a challenging problem because, characters in these documents are often touching or broken due to degradation/agei...
Partha Pratim Roy, Jean-Yves Ramel, Nicolas Ragot
TCC
2012
Springer
218views Cryptology» more  TCC 2012»
14 years 2 months ago
Iterative Constructions and Private Data Release
In this paper we study the problem of approximately releasing the cut function of a graph while preserving differential privacy, and give new algorithms (and new analyses of exis...
Anupam Gupta, Aaron Roth, Jonathan Ullman