Noise-Contrastive Estimation for Multivariate Point Processes
Explore the concepts of Noise-Contrastive Estimation (NCE) and Maximum Likelihood Estimation (MLE) for multivariate point processes. Learn about the differences, complexities, and applications of these estimation methods in data analysis.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Noise-Contrastive Estimation for Multivariate Point Processes Hongyuan Mei, Tom Wan, Jason Eisner Johns Hopkins University
MLE: Max log prob of data NOW dt = infinitesimal time=0 t t + dt 5dt A B A C A 7dt B C 2dt Loop over all 50000 event types! (A, B, C, ) 1-(5+7+2)dt 1 Integrate over infinitely many non-events! (often approx by sampling) SLOW 1
NCE: Max log prob of correct discrimination time=0 B A C A Loop over real and noise events finite & small faster SGD B A C B C A Which Is Real? 2
NCE vs MLE: what it typically looks like # of probabilities computed wall-clock time 3
NCE: More in paper theorems & proofs more results & analysis 4
THANK YOU Hongyuan Mei, Tom Wan, Jason Eisner Johns Hopkins University
