English
Related papers

Related papers: A Bayesian Approach to Invariant Deep Neural Netwo…

200 papers

The analytic inference, e.g. predictive distribution being in closed form, may be an appealing benefit for machine learning practitioners when they treat wide neural networks as Gaussian process in Bayesian setting. The realistic widths,…

Disordered Systems and Neural Networks · Physics 2023-08-01 Chi-Ken Lu

Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction. Unfortunately, the unique symmetry structure of deep weight spaces makes this design very…

Machine Learning · Computer Science 2023-06-02 Aviv Navon , Aviv Shamsian , Idan Achituve , Ethan Fetaya , Gal Chechik , Haggai Maron

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that…

Machine Learning · Computer Science 2014-10-28 Misha Denil , Babak Shakibi , Laurent Dinh , Marc'Aurelio Ranzato , Nando de Freitas

One of the goals of probabilistic inference is to decide whether an empirically observed distribution is compatible with a candidate Bayesian network. However, Bayesian networks with hidden variables give rise to highly non-trivial…

Machine Learning · Statistics 2014-10-14 R. Chaves , L. Luft , T. O. Maciel , D. Gross , D. Janzing , B. Schölkopf

This paper considers the problem of learning the parameters in Bayesian networks of discrete variables with known structure and hidden variables. Previous approaches in these settings typically use expectation maximization; when the network…

Machine Learning · Computer Science 2013-09-27 Yonatan Halpern , David Sontag

Bayesian neural Networks (BNNs) are a promising method of obtaining statistical uncertainties for neural network predictions but with a higher computational overhead which can limit their practical usage. This work explores the use of high…

Machine Learning · Computer Science 2020-09-09 Himanshu Sharma , Elise Jennings

We introduce an algorithm where the individual bits representing the weights of a neural network are learned. This method allows training weights with integer values on arbitrary bit-depths and naturally uncovers sparse networks, without…

Machine Learning · Computer Science 2022-02-22 Cristian Ivan

Data augmentation is commonly applied to improve performance of deep learning by enforcing the knowledge that certain transformations on the input preserve the output. Currently, the data augmentation parameters are chosen by human effort…

Despite much research targeted at enabling conventional machine learning models to continually learn tasks and data distributions sequentially without forgetting the knowledge acquired, little effort has been devoted to account for more…

Machine Learning · Computer Science 2021-06-11 Sandra Servia-Rodriguez , Cecilia Mascolo , Young D. Kwon

Three important properties of a classification machinery are: (i) the system preserves the core information of the input data; (ii) the training examples convey information about unseen data; and (iii) the system is able to treat…

Neural and Evolutionary Computing · Computer Science 2016-06-29 Raja Giryes , Guillermo Sapiro , Alex M. Bronstein

Natural image statistics exhibit hierarchical dependencies across multiple scales. Representing such prior knowledge in non-factorial latent tree models can boost performance of image denoising, inpainting, deconvolution or reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2012-07-03 Young Jun Ko , Matthias Seeger

Structured sparsity has recently emerged in statistics, machine learning and signal processing as a promising paradigm for learning in high-dimensional settings. All existing methods for learning under the assumption of structured sparsity…

Machine Learning · Statistics 2015-09-16 Nino Shervashidze , Francis Bach

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning…

Machine Learning · Computer Science 2024-07-04 Cuong Pham , Cuong C. Nguyen , Trung Le , Dinh Phung , Gustavo Carneiro , Thanh-Toan Do

We address the problem of Bayesian structure learning for domains with hundreds of variables by employing non-parametric bootstrap, recursively. We propose a method that covers both model averaging and model selection in the same framework.…

Machine Learning · Statistics 2018-09-14 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Guy Koren , Gal Novik

Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph data. The most flexible approach to constructing the sheaf is…

Machine Learning · Computer Science 2025-09-15 Patrick Gillespie , Layal Bou Hamdan , Ioannis Schizas , David L. Boothe , Vasileios Maroulas

Mechanistic models of single-neuron dynamics have been extensively studied in computational neuroscience. However, identifying which models can quantitatively reproduce empirically measured data has been challenging. We propose to overcome…

Ensembling can improve the performance of Neural Networks, but existing approaches struggle when the architecture likelihood surface has dispersed, narrow peaks. Furthermore, existing methods construct equally weighted ensembles, and this…

Machine Learning · Statistics 2023-03-20 Saad Hamid , Xingchen Wan , Martin Jørgensen , Binxin Ru , Michael Osborne

We propose a new approach to Bayesian prediction that caters for models with a large number of parameters and is robust to model misspecification. Given a class of high-dimensional (but parametric) predictive models, this new approach…

Methodology · Statistics 2022-05-13 David T. Frazier , Ruben Loaiza-Maya , Gael M. Martin , Bonsoo Koo

We consider the use of deep learning for covariance estimation. We propose to globally learn a neural network that will then be applied locally at inference time. Leveraging recent advancements in self-supervised foundational models, we…

Signal Processing · Electrical Eng. & Systems 2024-03-14 Tzvi Diskin , Ami Wiesel