Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Boosting Variational Inference With Locally Adaptive Step-Sizes (2105.09240v1)

Published 19 May 2021 in cs.LG and stat.ML

Abstract: Variational Inference makes a trade-off between the capacity of the variational family and the tractability of finding an approximate posterior distribution. Instead, Boosting Variational Inference allows practitioners to obtain increasingly good posterior approximations by spending more compute. The main obstacle to widespread adoption of Boosting Variational Inference is the amount of resources necessary to improve over a strong Variational Inference baseline. In our work, we trace this limitation back to the global curvature of the KL-divergence. We characterize how the global curvature impacts time and memory consumption, address the problem with the notion of local curvature, and provide a novel approximate backtracking algorithm for estimating local curvature. We give new theoretical convergence rates for our algorithms and provide experimental validation on synthetic and real-world datasets.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Gideon Dresdner (9 papers)
  2. Saurav Shekhar (1 paper)
  3. Fabian Pedregosa (48 papers)
  4. Francesco Locatello (92 papers)
  5. Gunnar Rätsch (59 papers)
Citations (2)

Summary

We haven't generated a summary for this paper yet.