English
Related papers

Related papers: SGD for Variational Inference: Tackling Unbounded …

200 papers

In this paper we propose and analyze a novel multilevel version of Stein variational gradient descent (SVGD). SVGD is a recent particle based variational inference method. For Bayesian inverse problems with computationally expensive…

Numerical Analysis · Mathematics 2024-02-05 Simon Weissmann , Jakob Zech

Modern neural network architectures have achieved remarkable accuracies but remain highly dependent on their training data, often lacking interpretability in their learned mappings. While effective on large datasets, they tend to overfit on…

Machine Learning · Computer Science 2025-03-19 Pavia Bera , Sanjukta Bhanja

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

Machine Learning · Statistics 2018-12-04 Xiaowu Dai , Yuhua Zhu

Stochastic Gradient Descent (SGD) with Polyak's stepsize has recently gained renewed attention in stochastic optimization. Recently, Orvieto, Lacoste-Julien, and Loizou introduced a decreasing variant of Polyak's stepsize, where convergence…

Optimization and Control · Mathematics 2025-07-01 Heinz H. Bauschke , Tran Thanh Tung

Probabilistic state estimation is essential for robots navigating uncertain environments. Accurately and efficiently managing uncertainty in estimated states is key to robust robotic operation. However, nonlinearities in robotic platforms…

Robotics · Computer Science 2024-11-19 Min-Won Seo , Solmaz S. Kia

We introduce Support Decomposition Variational Inference (SDVI), a new variational inference (VI) approach for probabilistic programs with stochastic support. Existing approaches to this problem rely on designing a single global variational…

Machine Learning · Computer Science 2023-11-02 Tim Reichelt , Luke Ong , Tom Rainforth

Partition functions arise in a variety of settings, including conditional random fields, logistic regression, and latent gaussian models. In this paper, we consider semistochastic quadratic bound (SQB) methods for maximum likelihood…

Machine Learning · Statistics 2014-02-19 Aleksandr Y. Aravkin , Anna Choromanska , Tony Jebara , Dimitri Kanevsky

Bayesian (deep) neural networks (BNN) are often more attractive than the vanilla point-estimate deep learning in various aspects including uncertainty quantification, robustness to noise, resistance to overfitting, and more. The variational…

Machine Learning · Computer Science 2026-05-22 Minyoung Kim

In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus…

Machine Learning · Statistics 2021-06-14 Kangqiao Liu , Liu Ziyin , Masahito Ueda

Geoscientists use observed data to estimate properties of the Earth's interior. This often requires non-linear inverse problems to be solved and uncertainties to be estimated. Bayesian inference solves inverse problems under a probabilistic…

Geophysics · Physics 2024-01-01 Xuebin Zhao , Andrew Curtis

The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been…

Machine Learning · Statistics 2019-02-28 Rui Shu , Hung H. Bui , Jay Whang , Stefano Ermon

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization…

Machine Learning · Computer Science 2021-01-29 Samuel L. Smith , Benoit Dherin , David G. T. Barrett , Soham De

Variational inference methods for latent variable statistical models have gained popularity because they are relatively fast, can handle large data sets, and have deterministic convergence guarantees. However, in practice it is unclear…

Methodology · Statistics 2017-03-22 Hachem Saddiki , Andrew C. Trapp , Patrick Flaherty

Stochastic variational inference (SVI), the state-of-the-art algorithm for scaling variational inference to large-datasets, is inherently serial. Moreover, it requires the parameters to fit in the memory of a single processor; this is…

It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size. In this work, we…

Machine Learning · Computer Science 2018-01-09 Dong Yin , Ashwin Pananjady , Max Lam , Dimitris Papailiopoulos , Kannan Ramchandran , Peter Bartlett

Variational inference (VI) is widely used for approximate inference in Bayesian machine learning. In addition to this practical success, generalization bounds for variational inference and related algorithms have been developed, mostly…

Machine Learning · Computer Science 2025-02-19 Yadi Wei , Roni Khardon

We propose an analytical solution for approximating the gradient of the Evidence Lower Bound (ELBO) in variational inference problems where the statistical model is a Bayesian network consisting of observations drawn from a mixture of a…

Machine Learning · Computer Science 2025-04-14 Roumen Nikolaev Popov

Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization…

Machine Learning · Computer Science 2019-03-12 Xinyu Peng , Li Li , Fei-Yue Wang

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

Machine Learning · Computer Science 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

Stochastic Gradient Descent with a constant learning rate (constant SGD) simulates a Markov chain with a stationary distribution. With this perspective, we derive several new results. (1) We show that constant SGD can be used as an…

Machine Learning · Statistics 2018-01-23 Stephan Mandt , Matthew D. Hoffman , David M. Blei
‹ Prev 1 4 5 6 7 8 10 Next ›