Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

37

ICML
2009
IEEE

favoriteEmaildiscussreport

136views Machine Learning» more ICML 2009»

Herding dynamical weights to learn

14 years 11 months ago

Herding dynamical weights to learn

Download www.ics.uci.edu

A new "herding" algorithm is proposed which directly converts observed moments into a sequence of pseudo-samples. The pseudosamples respect the moment constraints and may be used to estimate (unobserved) quantities of interest. The procedure allows us to sidestep the usual approach of first learning a joint model (which is intractable) and then sampling from that model (which can easily get stuck in a local mode). Moreover, the algorithm is fully deterministic, avoiding random number generation) and does not need expensive operations such as exponentiation.

Max Welling

Real-time Traffic

ICML 2009 | Machine Learning | Moment Constraints | Observed Moments | Random Number Generation |

claim paper

Related Content

» Parametric Herding

» Dynamic Matching via Weighted Myopia with Application to Kidney Exchange

» On the weight dynamics of recurrent learning

» Correlation learning rule in floatinggate pFET synapses

» Dynamic Weighted Majority A New Ensemble Method for Tracking Concept Drift

» Dynamic preferences in multicriteria reinforcement learning

» Learning using Dynamical Regime Identification and Synchronization

» Dynamics of Learning Algorithms for the OnDemand Secure Byzantine Routing Protocol

» An Ensemble Approach for Incremental Learning in Nonstationary Environments

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	2009
Where	ICML
Authors	Max Welling

Comments (0)