English
Related papers

Related papers: Central Limit Theorem for Bayesian Neural Network …

200 papers

We show at a physics level of rigor that Bayesian inference with a fully connected neural network and a shaped nonlinearity of the form $\phi(t) = t + \psi t^3/L$ is (perturbatively) solvable in the regime where the number of training…

Machine Learning · Statistics 2024-05-28 Boris Hanin , Alexander Zlokapa

While Contrastive Learning (CL) has revolutionized self-supervised representation learning, its latent representations remain highly entangled and opaque, limiting their interpretability in safety-critical applications. We identify that a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Peng Cui , Jiahao Zhang , Lijie Hu

Sample covariance matrices are widely used in multivariate statistical analysis. The central limit theorems (CLT's) for linear spectral statistics of high-dimensional non-centered sample covariance matrices have received considerable…

Methodology · Statistics 2014-04-29 Shurong Zheng , Z. D. Bai , Jiangfeng Yao

We establish a central limit theorem (CLT) for families of products of $\epsilon$-independent random variables. We utilize graphon limits to encode the evolution of independence and characterize the limiting distribution. Our framework…

Probability · Mathematics 2025-04-15 Guillaume Cébron , Patrick Oliveira Santos , Pierre Youssef

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that…

Machine Learning · Statistics 2022-07-08 Inbar Seroussi , Ofer Zeitouni

In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex…

Machine Learning · Computer Science 2023-11-10 Anshuk Uppal , Kristoffer Stensbo-Smidt , Wouter Boomsma , Jes Frellsen

This study introduces a new normalization layer termed Batch Layer Normalization (BLN) to reduce the problem of internal covariate shift in deep neural network layers. As a combined version of batch and layer normalization, BLN adaptively…

Machine Learning · Computer Science 2023-01-16 Amir Ziaee , Erion Çano

This paper provides a Central Limit Theorem (CLT) for a process $\{\theta_n, n\geq 0\}$ satisfying a stochastic approximation (SA) equation of the form $\theta_{n+1} = \theta_n + \gamma_{n+1} H(\theta_n,X_{n+1})$; a CLT for the associated…

Probability · Mathematics 2013-09-13 Gersende Fort

Sequential Bayesian inference over predictive functions is a natural framework for continual learning from streams of data. However, applying it to neural networks has proved challenging in practice. Addressing the drawbacks of existing…

Machine Learning · Statistics 2023-12-29 Tim G. J. Rudner , Freddie Bickford Smith , Qixuan Feng , Yee Whye Teh , Yarin Gal

Learning internal representations from data using no or few labels is useful for machine learning research, as it allows using massive amounts of unlabeled data. In this work, we use the Bayesian Confidence Propagation Neural Network…

Machine Learning · Computer Science 2021-06-30 Naresh Balaji Ravichandran , Anders Lansner , Pawel Herman

Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian…

Machine Learning · Computer Science 2019-10-23 Xinjie Lan , Kenneth E. Barner

As an effective and efficient discriminative learning method, Broad Learning System (BLS) has received increasing attention due to its outstanding performance in various regression and classification problems. However, the standard BLS is…

Machine Learning · Computer Science 2023-04-06 Yunfei Zheng , Badong Chen , Shiyuan Wang , Weiqun Wang

We study batch normalisation in the context of variational inference methods in Bayesian neural networks, such as mean-field or MC Dropout. We show that batch-normalisation does not affect the optimum of the evidence lower bound (ELBO).…

Machine Learning · Computer Science 2020-12-25 Jishnu Mukhoti , Puneet K. Dokania , Philip H. S. Torr , Yarin Gal

Over the last 30 years, extensive work has been devoted to developing central limit theory for partial sums of subordinated long memory linear time series. A much less studied problem, motivated by questions that are ubiquitous in extreme…

Probability · Mathematics 2026-03-24 Ioan Scheffel , Marco Oesting , Gilles Stupfler

We give a two-dimensional central limit theorem (CLT) for the second-order quadratic variation of the centered Gaussian processes on $[0,T]$. Though the approach we use is well known in the literature, the conditions under which the CLT…

Probability · Mathematics 2020-06-09 Kestutis Kubilius

In this paper, we study a stochastic strongly convex optimization problem and propose three classes of variable sample-size stochastic first-order methods including the standard stochastic gradient descent method, its accelerated variant,…

Optimization and Control · Mathematics 2024-05-08 Jinlong Lei , Uday V. Shanbhag

Concept bottleneck model (CBM) is a ubiquitous method that can interpret neural networks using concepts. In CBM, concepts are inserted between the output layer and the last intermediate layer as observable values. This helps in…

Machine Learning · Statistics 2023-03-17 Naoki Hayashi , Yoshihide Sawada

A efficient incremental learning algorithm for classification tasks, called NetLines, well adapted for both binary and real-valued input patterns is presented. It generates small compact feedforward neural networks with one hidden layer of…

Artificial Intelligence · Computer Science 2009-04-30 Juan-Manuel Torres-Moreno , Mirta B. Gordon

Bayesian networks in their Factor Graph Reduced Normal Form (FGrn) are a powerful paradigm for implementing inference graphs. Unfortunately, the computational and memory costs of these networks may be considerable, even for relatively small…

Machine Learning · Statistics 2021-06-22 Giovanni Di Gennaro , Amedeo Buonanno , Francesco A. N. Palmieri

Bayesian neural networks (BNNs) combine the expressive power of deep learning with the advantages of Bayesian formalism. In recent years, the analysis of wide, deep BNNs has provided theoretical insight into their priors and posteriors.…

Machine Learning · Computer Science 2022-02-24 Beau Coker , Wessel P. Bruinsma , David R. Burt , Weiwei Pan , Finale Doshi-Velez