Sciweavers

NIPS
2007
13 years 5 months ago
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods
Learning in real-world domains often requires to deal with continuous state and action spaces. Although many solutions have been proposed to apply Reinforcement Learning algorithm...
Alessandro Lazaric, Marcello Restelli, Andrea Bona...
NIPS
2007
13 years 5 months ago
The Tradeoffs of Large Scale Learning
This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms. The analysis shows distinct tradeoffs for...
Léon Bottou, Olivier Bousquet
NIPS
2007
13 years 5 months ago
Structured Learning with Approximate Inference
In many structured prediction problems, the highest-scoring labeling is hard to compute exactly, leading to the use of approximate inference methods. However, when inference is us...
Alex Kulesza, Fernando Pereira
NIPS
2007
13 years 5 months ago
Stability Bounds for Non-i.i.d. Processes
The notion of algorithmic stability has been used effectively in the past to derive tight generalization bounds. A key advantage of these bounds is that they are designed for spec...
Mehryar Mohri, Afshin Rostamizadeh
NETWORKING
2007
13 years 5 months ago
Reinforcement Learning-Based Load Shared Sequential Routing
We consider event dependent routing algorithms for on-line explicit source routing in MPLS networks. The proposed methods are based on load shared sequential routing in which load ...
Fariba Heidari, Shie Mannor, Lorne Mason
NIPS
2008
13 years 5 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
IJCAI
2007
13 years 5 months ago
Constructing New and Better Evaluation Measures for Machine Learning
Evaluation measures play an important role in machine learning because they are used not only to compare different learning algorithms, but also often as goals to optimize in cons...
Jin Huang, Charles X. Ling
ICONIP
2007
13 years 5 months ago
Practical Recurrent Learning (PRL) in the Discrete Time Domain
One of the authors has proposed a simple learning algorithm for recurrent neural networks, which requires computational cost and memory capacity in practical order O(n2 )[1]. The a...
Mohamad Faizal Bin Samsudin, Takeshi Hirose, Katsu...
ICMLA
2008
13 years 5 months ago
New Insights into Learning Algorithms and Datasets
We report on three distinct experiments that provide new valuable insights into learning algorithms and datasets. We first describe two effective meta-features that significantly ...
Jun Won Lee, Christophe G. Giraud-Carrier
ICMLA
2008
13 years 5 months ago
Regularized Minimum Volume Ellipsoid Metric for Query-Based Learning
We are interested in learning an adaptive local metric on a lower dimensional manifold for query
Karim T. Abou-Moustafa, Frank P. Ferrie