English
Related papers

Related papers: Understanding Stochastic Natural Gradient Variatio…

200 papers

We present a unified framework to analyze the global convergence of Langevin dynamics based algorithms for nonconvex finite-sum optimization with $n$ component functions. At the core of our analysis is a direct analysis of the ergodicity of…

Machine Learning · Statistics 2020-10-20 Pan Xu , Jinghui Chen , Difan Zou , Quanquan Gu

Variance reduction (VR) methods employ stochastic gradients with decreasing variance, and they have been widely applied to solve large-scale optimization problems in machine learning because of their efficiency. Existing theoretical studies…

Machine Learning · Computer Science 2026-05-28 Yunwen Lei , Zimeng Wang , Xiaoming Yuan

Fractional derivatives are a well-studied generalization of integer order derivatives. Naturally, for optimization, it is of interest to understand the convergence properties of gradient descent using fractional derivatives. Convergence…

Optimization and Control · Mathematics 2024-06-05 Ashwani Aggarwal

Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergence, generates samples from a stationary distribution. We show…

Machine Learning · Statistics 2017-09-12 Stephan Mandt , Matthew D. Hoffman , David M. Blei

Understanding the gradient variance of black-box variational inference (BBVI) is a crucial step for establishing its convergence and developing algorithmic improvements. However, existing studies have yet to show that the gradient variance…

Machine Learning · Computer Science 2023-06-06 Kyurae Kim , Kaiwen Wu , Jisu Oh , Jacob R. Gardner

Variational inference is a powerful approach for approximate posterior inference. However, it is sensitive to initialization and can be subject to poor local optima. In this paper, we develop proximity variational inference (PVI). PVI is a…

Machine Learning · Statistics 2017-05-26 Jaan Altosaar , Rajesh Ranganath , David M. Blei

Posterior inference in directed graphical models is commonly done using a probabilistic encoder (a.k.a inference model) conditioned on the input. Often this inference model is trained jointly with the probabilistic decoder (a.k.a generator…

Machine Learning · Computer Science 2019-12-21 Amir Zadeh , Smon Hessner , Yao-Chong Lim , Louis-Phlippe Morency

One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation…

Computation · Statistics 2018-05-11 David M. Blei , Alp Kucukelbir , Jon D. McAuliffe

Variational empirical Bayes (VEB) methods provide a practically attractive approach to fitting large, sparse, multiple regression models. These methods usually use coordinate ascent to optimize the variational objective function, an…

Methodology · Statistics 2024-11-25 Saikat Banerjee , Peter Carbonetto , Matthew Stephens

Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational families by considering implicit variational distributions defined in a hierarchical manner. However, due to the intractable densities of…

Machine Learning · Statistics 2023-08-22 Longlin Yu , Cheng Zhang

We develop EigenVI, an eigenvalue-based approach for black-box variational inference (BBVI). EigenVI constructs its variational approximations from orthogonal function expansions. For distributions over $\mathbb{R}^D$, the lowest order term…

Machine Learning · Statistics 2024-11-01 Diana Cai , Chirag Modi , Charles C. Margossian , Robert M. Gower , David M. Blei , Lawrence K. Saul

In this paper, we investigate the theoretical properties of stochastic gradient descent (SGD) for statistical inference in the context of nonconvex optimization problems, which have been relatively unexplored compared to convex settings.…

Machine Learning · Statistics 2023-06-06 Yanjie Zhong , Todd Kuffner , Soumendra Lahiri

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

Machine Learning · Computer Science 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman

Stochastic planning can be reduced to probabilistic inference in large discrete graphical models, but hardness of inference requires approximation schemes to be used. In this paper we argue that such applications can be disentangled along…

Artificial Intelligence · Computer Science 2022-09-05 Zhennan Wu , Roni Khardon

We consider the problem of minimizing the average of a large number of smooth but possibly non-convex functions. In the context of most machine learning applications, each loss function is non-negative and thus can be expressed as the…

Optimization and Control · Mathematics 2024-07-08 Antonio Orvieto , Lin Xiao

Stochastic gradient methods are scalable for solving large-scale optimization problems that involve empirical expectations of loss functions. Existing results mainly apply to optimization problems where the objectives are one- or two-level…

Optimization and Control · Mathematics 2018-01-15 Shuoguang Yang , Mengdi Wang , Ethan X. Fang

We firstly propose the new stochastic gradient estimate of unbiasedness and minimized variance in this paper. Secondly, we propose the two algorithms: Algorithml and Algorithm2 which apply the new stochastic gradient estimate to modern…

Optimization and Control · Mathematics 2023-06-02 Feifei Gao , Caixia Kou

Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows…

Machine Learning · Computer Science 2017-06-06 Maxim Raginsky , Alexander Rakhlin , Matus Telgarsky

Black-box variational inference (BBVI) with Gaussian mixture families offers a flexible approach for approximating complex posterior distributions without requiring gradients of the target density. However, standard numerical optimization…

Machine Learning · Computer Science 2026-05-29 Baojun Che , Yifan Chen , Daniel Zhengyu Huang , Xinying Mao , Weijie Wang

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.…

Machine Learning · Computer Science 2020-02-14 Yixuan Qiu , Xiao Wang
‹ Prev 1 3 4 5 6 7 10 Next ›