English
Related papers

Related papers: Natural Gradient VI: Guarantees for Non-Conjugate …

200 papers

Stochastic-gradient sampling methods are often used to perform Bayesian inference on neural networks. It has been observed that the methods in which notions of differential geometry are included tend to have better performances, with the…

Machine Learning · Computer Science 2024-04-02 Hanlin Yu , Marcelo Hartmann , Bernardo Williams , Arto Klami

Deep learning has revolutionized the last decade, being at the forefront of extraordinary advances in a wide range of tasks including computer vision, natural language processing, and reinforcement learning, to name but a few. However, it…

Machine Learning · Computer Science 2024-01-24 Sebastian W. Ober

The constrained gradient method (CGM) has recently been proposed to solve convex optimization and monotone variational inequality (VI) problems with general functional constraints. While existing literature has established convergence…

Optimization and Control · Mathematics 2025-11-24 Danqing Zhou , Hongmei Chen , Shiqian Ma , Junfeng Yang

Stochastic gradient descent (SGD) algorithm is the method of choice in many machine learning tasks thanks to its scalability and efficiency in dealing with large-scale problems. In this paper, we focus on the shuffling version of SGD which…

Machine Learning · Computer Science 2023-10-27 Lam M. Nguyen , Trang H. Tran

In this paper, we propose CI-VI an efficient and scalable solver for semi-implicit variational inference (SIVI). Our method, first, maps SIVI's evidence lower bound (ELBO) to a form involving a nonlinear functional nesting of expected…

Machine Learning · Computer Science 2021-01-18 Vincent Moens , Hang Ren , Alexandre Maraval , Rasul Tutunov , Jun Wang , Haitham Ammar

Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by using stochastic gradient descent (SGD), theoretical analysis…

Machine Learning · Computer Science 2022-02-21 Harsh Vardhan , Sebastian U. Stich

In variational inference (VI), the practitioner approximates a high-dimensional distribution $\pi$ with a simple surrogate one, often a (product) Gaussian distribution. However, in many cases of practical interest, Gaussian distributions…

Machine Learning · Computer Science 2026-04-01 Luca Ghafourpour , Sinho Chewi , Alessio Figalli , Aram-Alexandre Pooladian

In this work, we investigate the large-scale mean-field variational inference (MFVI) problem from a mini-batch primal-dual perspective. By reformulating MFVI as a constrained finite-sum problem, we develop a novel primal-dual algorithm…

Machine Learning · Statistics 2026-02-11 Jinhua Lyu , Tianmin Yu , Ying Ma , Naichen Shi

Continual learning in neural networks aims to learn new tasks without forgetting old tasks. Sequential function-space variational inference (SFSVI) uses a Gaussian variational distribution to approximate the distribution of the outputs of…

Machine Learning · Computer Science 2025-05-28 Menghao Waiyan William Zhu , Pengcheng Hao , Ercan Engin Kuruoğlu

Instrumental variables (IVs) provide a powerful strategy for identifying causal effects in the presence of unobservable confounders. Within the nonparametric setting (NPIV), recent methods have been based on nonlinear generalizations of…

Machine Learning · Statistics 2024-12-24 Yuri Fonseca , Caio Peixoto , Yuri Saporito

Inspired by dynamic programming, we propose Stochastic Virtual Gradient Descent (SVGD) algorithm where the Virtual Gradient is defined by computational graph and automatic differentiation. The method is computationally efficient and has…

Machine Learning · Computer Science 2019-08-01 Zheng Li , Shi Shu

We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors. We develop stochastic quadratic constraints to formulate a small linear matrix…

Optimization and Control · Mathematics 2020-03-31 Bin Hu , Peter Seiler , Laurent Lessard

A commonly used heuristic in non-convex optimization is Normalized Gradient Descent (NGD) - a variant of gradient descent in which only the direction of the gradient is taken into account and its magnitude ignored. We analyze this heuristic…

Machine Learning · Computer Science 2016-11-22 Kfir Y. Levy

We analyze stochastic gradient algorithms for optimizing nonconvex, nonsmooth finite-sum problems. In particular, the objective function is given by the summation of a differentiable (possibly nonconvex) component, together with a possibly…

Optimization and Control · Mathematics 2018-12-04 Zhize Li , Jian Li

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…

Statistics Theory · Mathematics 2023-04-13 Michael Diao , Krishnakumar Balasubramanian , Sinho Chewi , Adil Salim

We present a Gaussian Variational Inference (GVI) technique that can be applied to large-scale nonlinear batch state estimation problems. The main contribution is to show how to fit both the mean and (inverse) covariance of a Gaussian to…

Robotics · Computer Science 2020-04-13 Timothy D. Barfoot , James R. Forbes , David Yoon

Efficiently accessing the information contained in non-linear and high dimensional probability distributions remains a core challenge in modern statistics. Traditionally, estimators that go beyond point estimates are either categorized as…

Methodology · Statistics 2021-07-06 Philipp Frank , Reimar Leike , Torsten A. Enßlin

Bayesian inference has been broadly applied to statistical network analysis, but suffers from the expensive computational costs due to the nature of Markov chain Monte Carlo sampling algorithms. This paper proposes a novel and…

Computation · Statistics 2025-09-03 Dingbo Wu , Fangzheng Xie

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 consider the problem of approximating a function by an element of a nonlinear manifold which admits a differentiable parametrization, typical examples being neural networks with differentiable activation functions or tensor networks.…

Machine Learning · Computer Science 2026-04-20 Anthony Nouy , Agustín Somacal
‹ Prev 1 4 5 6 7 8 10 Next ›