Robust, Accurate Stochastic Optimization for Variational Inference

by   Akash Kumar Dhaka, et al.

We consider the problem of fitting variational posterior approximations using stochastic optimization methods. The performance of these approximations depends on (1) how well the variational family matches the true posterior distribution,(2) the choice of divergence, and (3) the optimization of the variational objective. We show that even in the best-case scenario when the exact posterior belongs to the assumed variational family, common stochastic optimization methods lead to poor variational approximations if the problem dimension is moderately large. We also demonstrate that these methods are not robust across diverse model types. Motivated by these findings, we develop a more robust and accurate stochastic optimization framework by viewing the underlying optimization algorithm as producing a Markov chain. Our approach is theoretically motivated and includes a diagnostic for convergence and a novel stopping rule, both of which are robust to noisy evaluations of the objective function. We show empirically that the proposed framework works well on a diverse set of models: it can automatically detect stochastic optimization failure or inaccurate variational approximation


page 1

page 2

page 3

page 4


Accelerating Stochastic Probabilistic Inference

Recently, Stochastic Variational Inference (SVI) has been increasingly a...

A Bayesian Variational Framework for Stochastic Optimization

This work proposes a theoretical framework for stochastic optimization a...

Robust, Automated, and Accurate Black-box Variational Inference

Black-box variational inference (BBVI) now sees widespread use in machin...

Scalable Estimation Algorithm for the DINA Q-matrix Combining Stochastic Optimization and Variational Inference

Diagnostic classification models (DCMs) enable finer-grained inspection ...

When can we improve on sample average approximation for stochastic optimization?

We explore the performance of sample average approximation in comparison...

The importance of better models in stochastic optimization

Standard stochastic optimization methods are brittle, sensitive to steps...

Bi-level Score Matching for Learning Energy-based Latent Variable Models

Score matching (SM) provides a compelling approach to learn energy-based...

Please sign up or login with your details

Forgot password? Click here to reset