Sciweavers

10 search results - page 2 / 2
» Asymptotic Analysis of Generative Semi-Supervised Learning
Sort
View
ICML
2008
IEEE
14 years 5 months ago
An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators
Statistical and computational concerns have motivated parameter estimators based on various forms of likelihood, e.g., joint, conditional, and pseudolikelihood. In this paper, we ...
Percy Liang, Michael I. Jordan
ML
2002
ACM
168views Machine Learning» more  ML 2002»
13 years 4 months ago
On Average Versus Discounted Reward Temporal-Difference Learning
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
John N. Tsitsiklis, Benjamin Van Roy
TSMC
2002
100views more  TSMC 2002»
13 years 4 months ago
Repetitive learning control: a Lyapunov-based approach
In this paper, a learning-based feedforward term is developed to solve a general control problem in the presence of unknown nonlinear dynamics with a known period. Since the learn...
Warren E. Dixon, Erkan Zergeroglu, Darren M. Dawso...
TCS
2010
13 years 3 months ago
Active learning in heteroscedastic noise
We consider the problem of actively learning the mean values of distributions associated with a finite number of options. The decision maker can select which option to generate t...
András Antos, Varun Grover, Csaba Szepesv&a...
CORR
2010
Springer
103views Education» more  CORR 2010»
13 years 5 months ago
On the Finite Time Convergence of Cyclic Coordinate Descent Methods
Cyclic coordinate descent is a classic optimization method that has witnessed a resurgence of interest in machine learning. Reasons for this include its simplicity, speed and stab...
Ankan Saha, Ambuj Tewari