Sciweavers

1206 search results - page 19 / 242
» Convergence analysis of online algorithms
Sort
View
NIPS
2008
13 years 10 months ago
From Online to Batch Learning with Cutoff-Averaging
We present cutoff averaging, a technique for converting any conservative online learning algorithm into a batch learning algorithm. Most online-to-batch conversion techniques work...
Ofer Dekel
IJON
2008
101views more  IJON 2008»
13 years 8 months ago
Learning dynamics and robustness of vector quantization and neural gas
Various alternatives have been developed to improve the Winner-Takes-All (WTA) mechanism in vector quantization, including the Neural Gas (NG). However, the behavior of these algo...
Aree Witoelar, Michael Biehl, Anarta Ghosh, Barbar...
ORL
2007
112views more  ORL 2007»
13 years 8 months ago
Competitive analysis of a dispatch policy for a dynamic multi-period routing problem
We analyze a simple and natural on-line algorithm (dispatch policy) for a dynamic multiperiod uncapacitated routing problem, in which at the beginning of each time period a set of...
Enrico Angelelli, Martin W. P. Savelsbergh, Maria ...
ICASSP
2011
IEEE
13 years 5 days ago
A general proof of convergence for adaptive distributed beamforming schemes
This work focuses on the convergence analysis of adaptive distributed beamforming schemes that can be reformulated as local random search algorithms via a random search framework....
Chang-Ching Chen, Chia-Shiang Tseng, Che Lin
ML
2007
ACM
131views Machine Learning» more  ML 2007»
13 years 8 months ago
A primal-dual perspective of online learning algorithms
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Shai Shalev-Shwartz, Yoram Singer