A Caltech Library Service

A Stochastic Interpretation of Stochastic Mirror Descent: Risk-Sensitive Optimality

Azizan, Navid and Hassibi, Babak (2019) A Stochastic Interpretation of Stochastic Mirror Descent: Risk-Sensitive Optimality. In: 2019 IEEE 58th Conference on Decision and Control (CDC). IEEE , Piscataway, NJ, pp. 3960-3965. ISBN 978-1-7281-1398-2.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Stochastic mirror descent (SMD) is a fairly new family of algorithms that has recently found a wide range of applications in optimization, machine learning, and control. It can be considered a generalization of the classical stochastic gradient algorithm (SGD), where instead of updating the weight vector along the negative direction of the stochastic gradient, the update is performed in a "mirror domain" defined by the gradient of a (strictly convex) potential function. This potential function, and the mirror domain it yields, provides considerable flexibility in the algorithm compared to SGD. While many properties of SMD have already been obtained in the literature, in this paper we exhibit a new interpretation of SMD, namely that it is a risk-sensitive optimal estimator when the unknown weight vector and additive noise are non-Gaussian and belong to the exponential family of distributions. The analysis also suggests a modified version of SMD, which we refer to as symmetric SMD (SSMD). The proofs rely on some simple properties of Bregman divergence, which allow us to extend results from quadratics and Gaussians to certain convex functions and exponential families in a rather seamless way.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Azizan, Navid0000-0002-4299-2963
Additional Information:© 2019 IEEE. This work was supported in part by the National Science Foundation under grants CCF-1423663, CCF-1409204 and ECCS-1509977, by a grant from Qualcomm Inc., by NASA’s Jet Propulsion Laboratory through the President and Director’s Fund, and by an Amazon (AWS) AI Fellowship.
Funding AgencyGrant Number
JPL President and Director's FundUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Record Number:CaltechAUTHORS:20190628-084200896
Persistent URL:
Official Citation:N. Azizan and B. Hassibi, "A Stochastic Interpretation of Stochastic Mirror Descent: Risk-Sensitive Optimality," 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019, pp. 3960-3965, doi: 10.1109/CDC40024.2019.9030229
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:96809
Deposited By: Tony Diaz
Deposited On:28 Jun 2019 17:10
Last Modified:16 Nov 2021 17:23

Repository Staff Only: item control page