Accession Number : ADA631612


Title :   Stochastic Models of Polymer Systems


Descriptive Note : Final rept. 15 Mar 2011-14 Mar 2014


Corporate Author : PRINCETON UNIV NJ


Personal Author(s) : E, Weinan ; Li, Qianxiao ; Tai, Cheng ; Wang, Chu ; Chazelle, Bernard


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a631612.pdf


Report Date : 01 Jan 2016


Pagination or Media Count : 7


Abstract : The stochastic gradient decent algorithm is the now the algorithm of choice for very large machine learning problems. We introduced the idea of stochastic modified equation to the analysis of such algorithms. This approach allows us to obtain very precise information about the behavior of the algorithm. At the same time, we were also able to formulate various acceleration techniques in precise math terms (e.g. formulate them as stochastic control problems) and obtain precise information about these acceleration methods. This approach is quite general and applies to other stochastic algorithms.


Descriptors :   *STOCHASTIC CONTROL , ALGORITHMS , BEHAVIOR , DIFFERENTIAL EQUATIONS , GRADIENTS , LEARNING MACHINES , MATHEMATICAL MODELS , PHASE TRANSFORMATIONS , POLYMERS , RELATIONAL DATA BASES , STATISTICAL PROCESSES , SYSTEMS ANALYSIS


Subject Categories : Statistics and Probability


Distribution Statement : APPROVED FOR PUBLIC RELEASE