Timezone: »
Oral
CRVI: Convex Relaxation for Variational Inference
Ghazal Fazelnia · John Paisley
We present a new technique for solving non-convex variational inference optimization problems. Variational inference is a widely used method for posterior approximation in which the inference problem is transformed into an optimization problem. For most models, this optimization is highly non-convex and so hard to solve. In this paper, we introduce a new approach to solving the variational inference optimization based on convex relaxation and semidefinite programming. Our theoretical results guarantee very tight relaxation bounds that get nearer to the global optimal solution than traditional coordinate ascent. We evaluate the performance of our approach on regression and sparse coding.
Author Information
Ghazal Fazelnia (Columbia University)
John Paisley (Columbia University)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Poster: CRVI: Convex Relaxation for Variational Inference »
Fri Jul 13th 04:15 -- 07:00 PM Room Hall B
More from the Same Authors
-
2019 Poster: Random Function Priors for Correlation Modeling »
Aonan Zhang · John Paisley -
2019 Oral: Random Function Priors for Correlation Modeling »
Aonan Zhang · John Paisley -
2018 Poster: Deep Bayesian Nonparametric Tracking »
Aonan Zhang · John Paisley -
2018 Oral: Deep Bayesian Nonparametric Tracking »
Aonan Zhang · John Paisley
