Variational Inference Problem

Variational inference (VI) is a powerful technique for approximating complex probability distributions, crucial in Bayesian machine learning and related fields. Current research focuses on addressing challenges like multimodality in Bayesian neural networks, improving efficiency in reinforcement learning (e.g., through variational delayed policy optimization), and scaling up algorithms like stochastic gradient descent for large datasets. These advancements aim to enhance the accuracy, efficiency, and scalability of VI, impacting diverse applications from improved model training in deep learning to more efficient solutions in complex decision-making problems.

Papers

October 8, 2024

Score-Based Variational Inference for Inverse Problems
Zhipeng Xue, Penghao Cai, Xiaojun Yuan, Xiqi Gao
Inverse Problem Backward Propagation Conditional Diffusion Diffusion Based Method Variational Inference Problem

August 10, 2024

Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks
Yoav Gelberg, Tycho F. A. van der Ouderaa, Mark van der Wilk, Yarin Gal
Variational Inference Bayesian Neural Network Weight Space Symmetric Model Variational Inference Problem Invariant Posterior

May 23, 2024

Variational Delayed Policy Optimization
Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Chao Huang
Reinforcement Learning State Augmentation Variational Inference Problem

April 16, 2024

Analytical Approximation of the ELBO Gradient in the Context of the Clutter Problem
Roumen Nikolaev Popov
Context Information Mean Field Dense Clutter Gradient Approximation Numerical Approximation Evidence Lower Bound Variational Inference Problem Gradient Covariance

October 20, 2022

On Representations of Mean-Field Variational Inference
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki, Edith Zhang
Variational Inference Meaningful Representation Mean Field Variational Bayesian Greedy Coordinate Variational Inference Problem

October 6, 2022

Scaling up Stochastic Gradient Descent for Non-convex Optimisation
Saad Mohamad, Hamad Alamri, Abdelhamid Bouchachia
Deep Reinforcement Learning Stochastic Gradient Descent Non Convex Optimization Variational Inference Problem

November 9, 2021

Variational Multi-Task Learning with Gumbel-Softmax Priors
Jiayi Shen, Xiantong Zhen, Marcel Worring, Ling Shao
Multi Task Learning Variational Posterior Gumbel Softmax Variational Inference Problem