Provable Bayesian Inference via Particle Mirror Descent
نویسندگان
چکیده
Since the prox-mapping of stochastic mirror descent is intractable when directly being applied to the optimization problem (1), we propose the -inexact prox-mapping within the stochastic mirror descent framework in Section 3. Instead of solving the prox-mapping exactly, we approximate the solution with error. In this section, we will show as long as the approximation error is tolerate, the stochastic mirror descent algorithm still converges. Theorem 2 Denote q∗ = argminq∈P L(q), the stochastic mirror descent with inexact prox-mapping after T steps gives
منابع مشابه
Scalable Bayesian Inference via Particle Mirror Descent
Bayesian methods are appealing in their flexibility in modeling complex data and ability in capturing uncertainty in parameters. However, when Bayes’ rule does not result in tractable closed-form, most approximate inference algorithms lack either scalability or rigorous guarantees. To tackle this challenge, we propose a simple yet provable algorithm, Particle Mirror Descent (PMD), to iterativel...
متن کاملStein Variational Gradient Descent: Theory and Applications
Although optimization can be done very efficiently using gradient-based optimization these days, Bayesian inference or probabilistic sampling has been considered to be much more difficult. Stein variational gradient descent (SVGD) is a new particle-based inference method derived using a functional gradient descent for minimizing KL divergence without explicit parametric assumptions. SVGD can be...
متن کاملHand Poste Estimation with Constrained Multi-hypotheses Gradient-Descent
In this report, we detail a novel approach to recover 3D hand pose from 2D images. To this end, we introduce a compact 3D hand model in a low dimension space where anatomy, kinematics and dynamics are implicitly inherited. The parameters of this model are recovered through a Bayesian inference approach. To this end, we propose an objective function which aims at separating the hand-skin charact...
متن کاملBayesian Inference of (Co) Variance Components and Genetic Parameters for Economic Traits in Iranian Holsteins via Gibbs Sampling
The aim of this study was using Bayesian approach via Gibbs sampling (GS) for estimating genetic parameters of production, reproduction and health traits in Iranian Holstein cows. Data consisted of 320666 first- lactation records of Holstein cows from 7696 sires and 260302 dams collected by the animal breeding center of Iran from year 1991 to 2010. (Co) variance components were estimated using ...
متن کاملRecasting Gradient-Based Meta-Learning as Hierarchical Bayes
Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task. Bayesian hierarchical modeling provides a theoretical framework for formalizing meta-learning as inference for a set of parameters that are shared across tasks. Here, we reformulate the model-agnostic meta-learning algorithm (MAML) of Finn et al. (2017) as ...
متن کامل