Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent

by   Frederik Kunstner, et al.

Expectation maximization (EM) is the default algorithm for fitting probabilistic models with missing or latent variables, yet we lack a full understanding of its non-asymptotic convergence properties. Previous works show results along the lines of "EM converges at least as fast as gradient descent" by assuming the conditions for the convergence of gradient descent apply to EM. This approach is not only loose, in that it does not capture that EM can make more progress than a gradient step, but the assumptions fail to hold for textbook examples of EM like Gaussian mixtures. In this work we first show that for the common setting of exponential family distributions, viewing EM as a mirror descent algorithm leads to convergence rates in Kullback-Leibler (KL) divergence. Then, we show how the KL divergence is related to first-order stationarity via Bregman divergences. In contrast to previous works, the analysis is invariant to the choice of parametrization and holds with minimal assumptions. We also show applications of these ideas to local linear (and superlinear) convergence rates, generalized EM, and non-exponential family distributions.


page 1

page 2

page 3

page 4


Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM

Many problems in machine learning can be formulated as optimizing a conv...

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

We study the Stein Variational Gradient Descent (SVGD) algorithm, which ...

On the Convergence of Policy in Unregularized Policy Mirror Descent

In this short note, we give the convergence analysis of the policy in th...

Bregman divergence based em algorithm and its application to classical and quantum rate distortion theory

We formulate em algorithm in the framework of Bregman divergence, which ...

Learning Behaviors with Uncertain Human Feedback

Human feedback is widely used to train agents in many domains. However, ...

Convergence Rates for the MAP of an Exponential Family and Stochastic Mirror Descent – an Open Problem

We consider the problem of upper bounding the expected log-likelihood su...

Divergence-Based Motivation for Online EM and Combining Hidden Variable Models

Expectation-Maximization (EM) is the fallback method for parameter estim...

Please sign up or login with your details

Forgot password? Click here to reset