paper-with-me

Papers

Robust, Accurate Stochastic Optimization for Variational Inference

2020-09-01 · NeurIPS 2020 12 · Akash Kumar Dhaka, Alejandro Catalina, Michael Riis Andersen, Måns Magnusson, Jonathan H. Huggins, Aki Vehtari

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

📄 PDF Abstract BibTeX arXiv:2009.00666

Code (0)

등록된 구현이 없습니다.

Tasks

DiagnosticStochastic OptimizationVariational Inference

Similar Papers 제목 키워드 기반

Fast Black-box Variational Inference through Stochastic Trust-Region Optimization

2017-06-07 · NeurIPS 2017 12 · Jeffrey Regier, Michael. I. Jordan, Jon Mcauliffe

We introduce TrustVI, a fast second-order algorithm for black-box variational inference based on trust-region optimization and the reparameterization trick. At each iteration, TrustVI proposes and assesses a step based o…

Variational Inference

Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes

2018-09-08 · Linfeng Liu, Li-Ping Liu

Inference for GP models with non-Gaussian noises is computationally expensive when dealing with large datasets. Many recent inference methods approximate the posterior distribution with a simpler distribution defined on …

Gaussian ProcessesStochastic OptimizationVariational Inference

Accelerating Stochastic Probabilistic Inference

2022-03-15 · Minta Liu, Suliang Bu

Recently, Stochastic Variational Inference (SVI) has been increasingly attractive thanks to its ability to find good posterior approximations of probabilistic models. It optimizes the variational objective with stochasti…

Second-order methodsStochastic OptimizationVariational Inference

Stochastic Collapsed Variational Inference for Sequential Data

2015-12-05 · Pengyu Wang, Phil Blunsom

Stochastic variational inference for collapsed models has recently been successfully applied to large scale topic modelling. In this paper, we propose a stochastic collapsed variational inference algorithm in the sequent…

Variational Inference

A Coreset-based, Tempered Variational Posterior for Accurate and Scalable Stochastic Gaussian Process Inference

2023-11-02 · Mert Ketenci, Adler Perotte, Noémie Elhadad, Iñigo Urteaga

We present a novel stochastic variational Gaussian process ($\mathcal{GP}$) inference method, based on a posterior over a learnable set of weighted pseudo input-output points (coresets). Instead of a free-form variationa…

Stochastic Optimization