Sciweavers

412 search results - page 33 / 83
» Algorithmic Complexity Bounds on Future Prediction Errors
Sort
View
115
Voted
COLT
2004
Springer
15 years 9 months ago
Convergence of Discrete MDL for Sequential Prediction
We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models....
Jan Poland, Marcus Hutter
152
Voted
FOCS
2009
IEEE
15 years 10 months ago
The Data Stream Space Complexity of Cascaded Norms
Abstract— We consider the problem of estimating cascaded aggregates over a matrix presented as a sequence of updates in a data stream. A cascaded aggregate P ◦Q is defined by ...
T. S. Jayram, David P. Woodruff
140
Voted
ML
2008
ACM
15 years 3 months ago
Margin-based first-order rule learning
Abstract We present a new margin-based approach to first-order rule learning. The approach addresses many of the prominent challenges in first-order rule learning, such as the comp...
Ulrich Rückert, Stefan Kramer
STOC
2009
ACM
123views Algorithms» more  STOC 2009»
16 years 4 months ago
An improved constant-time approximation algorithm for maximum~matchings
This paper studies constant-time approximation algorithms for problems on degree-bounded graphs. Let n and d be the number of vertices and the degree bound, respectively. This pap...
Yuichi Yoshida, Masaki Yamamoto, Hiro Ito
120
Voted
IPPS
2008
IEEE
15 years 10 months ago
Modeling and predicting application performance on parallel computers using HPC challenge benchmarks
A method is presented for modeling application performance on parallel computers in terms of the performance of microkernels from the HPC Challenge benchmarks. Specifically, the a...
Wayne Pfeiffer, Nicholas J. Wright