Stochastic Online Optimization using Kalman Recursion

02/10/2020
by   Joseph De Vilmarest, et al.
0

We study the Extended Kalman Filter in constant dynamics, offering a bayesian perspective of stochastic optimization. We obtain high probability bounds on the cumulative excess risk in an unconstrained setting. The unconstrained challenge is tackled through a two-phase analysis. First, for linear and logistic regressions, we prove that the algorithm enters a local phase where the estimate stays in a small region around the optimum. We provide explicit bounds with high probability on this convergence time. Second, for generalized linear regressions, we provide a martingale analysis of the excess risk in the local phase, improving existing ones in bounded stochastic optimization. The EKF appears as a parameter-free O(d^2) online algorithm that optimally solves some unconstrained optimization problems.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

03/22/2011

Randomized Smoothing for Stochastic Optimization

We analyze convergence rates of stochastic optimization procedures for n...
04/06/2013

Logical Stochastic Optimization

We present a logical framework to represent and reason about stochastic ...
02/12/2020

Online Learning of the Kalman Filter with Logarithmic Regret

In this paper, we consider the problem of predicting observations genera...
06/28/2021

High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails

We consider non-convex stochastic optimization using first-order algorit...
07/07/2021

KaFiStO: A Kalman Filtering Framework for Stochastic Optimization

Optimization is often cast as a deterministic problem, where the solutio...
05/24/2011

Ergodic Mirror Descent

We generalize stochastic subgradient descent methods to situations in wh...
12/30/2021

Risk-Bounded Control with Kalman Filtering and Stochastic Barrier Functions

In this paper, we study Stochastic Control Barrier Functions (SCBFs) to ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.