English
Related papers

Related papers: Approximate Gaussianity Beyond Initialisation in N…

200 papers

We propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty. This directly replaces convolving…

Machine Learning · Statistics 2021-04-29 Sebastian G. Popescu , David J. Sharp , James H. Cole , Konstantinos Kamnitsas , Ben Glocker

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

Machine Learning · Computer Science 2024-11-25 Jan Spörer , Bernhard Bermeitinger , Tomas Hrycej , Niklas Limacher , Siegfried Handschuh

The Bayesian treatment of neural networks dictates that a prior distribution is specified over their weight and bias parameters. This poses a challenge because modern neural networks are characterized by a large number of parameters, and…

Machine Learning · Statistics 2022-04-26 Ba-Hien Tran , Simone Rossi , Dimitrios Milios , Maurizio Filippone

We develop a framework for generalized variational inference in infinite-dimensional function spaces and use it to construct a method termed Gaussian Wasserstein inference (GWI). GWI leverages the Wasserstein distance between Gaussian…

Machine Learning · Statistics 2022-10-18 Veit D. Wild , Robert Hu , Dino Sejdinovic

The ability to represent and compare machine learning models is crucial in order to quantify subtle model changes, evaluate generative models, and gather insights on neural network architectures. Existing techniques for comparing data…

We study the efficacy and efficiency of deep generative networks for approximating probability distributions. We prove that neural networks can transform a low-dimensional source distribution to a distribution that is arbitrarily close to a…

Machine Learning · Computer Science 2023-12-05 Yunfei Yang , Zhen Li , Yang Wang

We introduce the Gaussian transform (GT), an optimal transport inspired iterative method for denoising and enhancing latent structures in datasets. Under the hood, GT generates a new distance function (GT distance) on a given dataset by…

Machine Learning · Computer Science 2020-06-23 Kun Jin , Facundo Mémoli , Zhengchao Wan

Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Greg Yang

This paper addresses a new active learning strategy for regression problems. The presented Wasserstein active regression model is based on the principles of distribution-matching to measure the representativeness of the labeled dataset. The…

Machine Learning · Computer Science 2024-03-25 Benjamin Bobbia , Matthias Picard

Inference for GP models with non-Gaussian noises is computationally expensive when dealing with large datasets. Many recent inference methods approximate the posterior distribution with a simpler distribution defined on a small number of…

Machine Learning · Computer Science 2018-09-11 Linfeng Liu , Liping Liu

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

Neural and Evolutionary Computing · Computer Science 2016-09-23 Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio

While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work…

Machine Learning · Computer Science 2019-07-02 Yu Bai , Tengyu Ma , Andrej Risteski

We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain…

Machine Learning · Computer Science 2024-06-18 Stefano Favaro , Boris Hanin , Domenico Marinucci , Ivan Nourdin , Giovanni Peccati

Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently. Here, we consider a richer prior distribution in…

Machine Learning · Statistics 2018-10-02 Theofanis Karaletsos , Peter Dayan , Zoubin Ghahramani

This paper uses sample data to study the problem of comparing populations on finite-dimensional parallelizable Riemannian manifolds and more general trivial vector bundles. Utilizing triviality, our framework represents populations as…

Methodology · Statistics 2023-11-29 Michael Wilson , Tom Needham , Chiwoo Park , Suprateek Kundu , Anuj Srivastava

Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is…

Machine Learning · Computer Science 2016-11-03 Hao Wang , Xingjian Shi , Dit-Yan Yeung

Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks…

Machine Learning · Computer Science 2021-12-20 Yu-Lin Tsai , Chia-Yi Hsu , Chia-Mu Yu , Pin-Yu Chen

To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by averaging predictions with respect to the posterior weight…

Machine Learning · Computer Science 2021-03-17 Jannik Schmitt , Stefan Roth

Covariance matrices have proven highly effective across many scientific fields. Since these matrices lie within the Symmetric Positive Definite (SPD) manifold - a Riemannian space with intrinsic non-Euclidean geometry, the primary challenge…

Machine Learning · Computer Science 2025-04-02 Rui Wang , Shaocheng Jin , Ziheng Chen , Xiaoqing Luo , Xiao-Jun Wu

In this paper we introduce a Wasserstein-type distance on the set of Gaussian mixture models. This distance is defined by restricting the set of possible coupling measures in the optimal transport problem to Gaussian mixture models. We…

Optimization and Control · Mathematics 2020-06-15 Julie Delon , Agnes Desolneux