Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00348935" target="_blank" >RIV/68407700:21230/20:00348935 - isvavai.cz</a>
Result on the web
<a href="https://neurips.cc/virtual/2020/public/poster_96fca94df72984fc97ee5095410d4dec.html" target="_blank" >https://neurips.cc/virtual/2020/public/poster_96fca94df72984fc97ee5095410d4dec.html</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
Original language description
In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochastic binary networks, obtained by adding noises in front of activations. The expected model response becomes a smooth function of parameters, its gradient is well defined but it is challenging to estimate it accurately. We propose a new method for this estimation problem combining sampling and analytic approximation steps. The method has a significantly reduced variance at the price of a small bias which gives a very practical tradeoff in comparison with existing unbiased and biased estimators. We further show that one extra linearization step leads to a deep straight-through estimator previously known only as an ad-hoc heuristic. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models with both proposed methods.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
ISBN
—
ISSN
1049-5258
e-ISSN
1049-5258
Number of pages
11
Pages from-to
—
Publisher name
Neural Information Processing Society
Place of publication
Montreal
Event location
Vancouver
Event date
Dec 6, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—