English
Related papers

Related papers: Langevin Dynamics with Continuous Tempering for Tr…

200 papers

Domain translation is the task of finding correspondence between two domains. Several Deep Neural Network (DNN) models, e.g., CycleGAN and cross-lingual language models, have shown remarkable successes on this task under the unsupervised…

Machine Learning · Computer Science 2020-09-01 Vignesh Srinivasan , Klaus-Robert Müller , Wojciech Samek , Shinichi Nakajima

We investigate the parameter space of transformer models trained on protein sequence data using a statistical mechanics framework, sampling the loss landscape at varying temperatures by Langevin dynamics to characterize the low-loss…

Disordered Systems and Neural Networks · Physics 2026-04-01 L. Ghiringhelli , A. Zambon , G. Tiana

In this work, we propose a Bayesian type sparse deep learning algorithm. The algorithm utilizes a set of spike-and-slab priors for the parameters in the deep neural network. The hierarchical Bayesian mixture will be trained using an…

Numerical Analysis · Mathematics 2021-03-17 Yating Wang , Wei Deng , Lin Guang

Sampling the parameter space of artificial neural networks according to a Boltzmann distribution provides insight into the geometry of low-loss solutions and offers an alternative to conventional loss minimization for training. However,…

Disordered Systems and Neural Networks · Physics 2026-03-17 Alessandro Zambon , Francesca Caruso , Riccardo Zecchina , Guido Tiana

Learning rate schedules are ubiquitously used to speed up and improve optimisation. Many different policies have been introduced on an empirical basis, and theoretical analyses have been developed for convex settings. However, in many…

Machine Learning · Computer Science 2022-02-10 Stéphane d'Ascoli , Maria Refinetti , Giulio Biroli

Monte Carlo sampling for Bayesian posterior inference is a common approach used in machine learning. The Markov Chain Monte Carlo procedures that are used are often discrete-time analogues of associated stochastic differential equations…

Machine Learning · Statistics 2020-02-14 Xiaocheng Shang , Zhanxing Zhu , Benedict Leimkuhler , Amos J. Storkey

Annealing-based neural samplers seek to amortize sampling from unnormalized distributions by training neural networks to transport a family of densities interpolating from source to target. A crucial design choice in the training phase of…

Machine Learning · Computer Science 2025-09-03 Ezra Erives , Bowen Jing , Peter Holderrieth , Tommi Jaakkola

In this paper we consider a new probability sampling methods based on Langevin diffusion dynamics to resolve the problem of existing Monte Carlo algorithms when draw samples from high dimensional target densities. We extent…

Machine Learning · Computer Science 2025-03-31 Z. Zarezadeh , N. Zarezadeh

This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA)…

Machine Learning · Statistics 2017-06-16 Simone Scardapane , Paolo Di Lorenzo

Traditionally, neural networks are parameterized using optimization procedures such as stochastic gradient descent, RMSProp and ADAM. These procedures tend to drive the parameters of the network toward a local minimum. In this article, we…

Machine Learning · Computer Science 2020-01-07 Benedict Leimkuhler , Charles Matthews , Tiffany Vlaar

We consider the sampling problem, where the aim is to draw samples from a distribution whose density is known only up to a normalization constant. Recent breakthroughs in generative modeling to approximate a high-dimensional data…

Hyperparameter optimization is both a practical issue and an interesting theoretical problem in training of deep architectures. Despite many recent advances the most commonly used methods almost universally involve training multiple and…

Machine Learning · Computer Science 2019-09-10 Vlad Pushkarov , Jonathan Efroni , Mykola Maksymenko , Maciej Koch-Janusz

Geometric tempering is a popular approach to sampling from challenging multi-modal probability distributions by instead sampling from a sequence of distributions which interpolate, using the geometric mean, between an easier proposal…

Machine Learning · Statistics 2025-04-09 Omar Chehab , Anna Korba , Austin Stromme , Adrien Vacher

While gradient-based discrete samplers are effective in sampling from complex distributions, they are susceptible to getting trapped in local minima, particularly in high-dimensional, multimodal discrete distributions, owing to the…

Machine Learning · Statistics 2025-05-21 Luxu Liang , Yuhang Jia , Feng Zhou

We recapitulate the Bayesian formulation of neural network based classifiers and show that, while sampling from the posterior does indeed lead to better generalisation than is obtained by standard optimisation of the cost function, even…

Machine Learning · Statistics 2019-04-09 Robert J. N. Baldock , Nicola Marzari

Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…

Computer Vision and Pattern Recognition · Computer Science 2016-06-15 Maya Kabkab , Azadeh Alavi , Rama Chellappa

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. The proposed algorithm is essentially a…

Machine Learning · Statistics 2022-05-24 Wei Deng , Guang Lin , Faming Liang

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and…

Machine Learning · Computer Science 2020-12-21 Shubhankar Gahlot , Junqi Yin , Mallikarjun Shankar

Learning multiple tasks sequentially requires neural networks to balance retaining knowledge, yet being flexible enough to adapt to new tasks. Regularizing network parameters is a common approach, but it rarely incorporates prior knowledge…

Machine Learning · Computer Science 2025-12-22 Joanna Sliwa , Frank Schneider , Nathanael Bosch , Agustinus Kristiadi , Philipp Hennig

Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices. Bayesian approaches to learning benefit from offering more information as…

Machine Learning · Computer Science 2021-07-16 Vyacheslav Kungurtsev , Adam Cobb , Tara Javidi , Brian Jalaian