【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...Deep Learning JP
?
The document proposes a method called SUMO (Stochastically Unbiased Marginalization Objective) for estimating log marginal probabilities in latent variable models. SUMO uses a Russian roulette estimator to obtain an unbiased estimate of the log marginal likelihood. This allows SUMO to provide an objective function for variational inference that converges to the log marginal likelihood as more samples are taken, avoiding the bias issues of methods like VAEs and IWAE. The paper outlines SUMO, compares it to existing methods, and demonstrates its effectiveness on density estimation tasks.
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...Deep Learning JP
?
The document proposes a method called SUMO (Stochastically Unbiased Marginalization Objective) for estimating log marginal probabilities in latent variable models. SUMO uses a Russian roulette estimator to obtain an unbiased estimate of the log marginal likelihood. This allows SUMO to provide an objective function for variational inference that converges to the log marginal likelihood as more samples are taken, avoiding the bias issues of methods like VAEs and IWAE. The paper outlines SUMO, compares it to existing methods, and demonstrates its effectiveness on density estimation tasks.
狠狠撸s by Louis Monier (Altavista Co-Founder & CTO) for Deep Learning keynote #1 at Holberton School. The keynote was followed by a workshop prepared by Gregory Renard. If you want to assist to similar keynote for free, checkout http://www.meetup.com/Holberton-School/
Deck used for my talk during PyDataNYC in which I described how we improved thumbnail cropping in our news app, Kamelio. We used Deep Learning object detection to identify the interesting regions of the image which was subsequently fed into image cropping logic.
2. 論文
Inverting Convolutional Networks
with Convolutional Networks
Alexey Dosovitskiy Thomas Brox
Department of Computer Science University of Freiburg, Germany
Quote [1]