paper-with-me

Papers

Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space

2023-04-10 · Michael Diao, Krishnakumar Balasubramanian, Sinho Chewi, Adil Salim

Variational inference (VI) seeks to approximate a target distribution $\pi$ by an element of a tractable family of distributions. Of key interest in statistics and machine learning is Gaussian VI, which approximates $\pi$ by minimizing the Kullback-Leibler (KL) divergence to $\pi$ over the space of Gaussians. In this work, we develop the (Stochastic) Forward-Backward Gaussian Variational Inference (FB-GVI) algorithm to solve Gaussian VI. Our approach exploits the composite structure of the KL divergence, which can be written as the sum of a smooth term (the potential) and a non-smooth term (the entropy) over the Bures-Wasserstein (BW) space of Gaussians endowed with the Wasserstein distance. For our proposed algorithm, we obtain state-of-the-art convergence guarantees when $\pi$ is log-smooth and log-concave, as well as the first convergence guarantees to first-order stationary solutions when $\pi$ is only log-smooth.

📄 PDF Abstract BibTeX arXiv:2304.05398

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold

2024-10-03 · Hoang Phuc Hau Luu, Hanlin Yu, Bernardo Williams, Marcelo Hartmann 외

Optimization in the Bures-Wasserstein space has been gaining popularity in the machine learning community since it draws connections between variational inference and Wasserstein gradient flows. The variational inference…

Variational Inference

Bridging the Gap Between Variational Inference and Wasserstein Gradient Flows

2023-10-31 · Mingxuan Yi, Song Liu

Variational inference is a technique that approximates a target distribution by optimizing within the parameter space of variational families. On the other hand, Wasserstein gradient flows describe optimization within th…

Variational Inference

Structured Variational Inference in Unstable Gaussian Process State Space Models

2019-07-16 · Silvan Melchior, Sebastian Curi, Felix Berkenkamp, Andreas Krause

We propose a new variational inference algorithm for learning in Gaussian Process State-Space Models (GPSSMs). Our algorithm enables learning of unstable and partially observable systems, where previous algorithms fail. …

Gaussian ProcessesState Space ModelsVariational Inference

Structured Variational Inference in Partially Observable Unstable Gaussian Process State Space Models

2020-06-08 · L4DC 2020 6 · Sebastian Curi, Silvan Melchior, Felix Berkenkamp, Andreas Krause

We propose a new variational inference algorithm for learning in Gaussian Process State-Space Models (GPSSMs). Our algorithm enables learning of unstable and partially observable systems, where previous algorithms fail. …

State Space ModelsVariational Inference

Variational inference via Wasserstein gradient flows

2022-05-31 · Marc Lambert, Sinho Chewi, Francis Bach, Silvère Bonnabel 외

Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI) has emerged as a central computational approach to large-scale Bayesian inference. Rather than sampling from the true posterior $\pi$, VI aim…

Bayesian InferenceVariational Inference