English
Related papers

Related papers: Intelligent Matrix Exponentiation

200 papers

The monotonic dependence of the outputs of a neural network on some of its inputs is a crucial inductive bias in many scenarios where domain knowledge dictates such behavior. This is especially important for interpretability and fairness…

Machine Learning · Computer Science 2023-07-17 Ouail Kitouni , Niklas Nolte , Michael Williams

Matrix factorization techniques have been widely used as a method for collaborative filtering for recommender systems. In recent times, different variants of deep learning algorithms have been explored in this setting to improve the task of…

Machine Learning · Computer Science 2019-03-26 Vaibhav Krishna , Tian Guo , Nino Antulov-Fantulin

We introduce a learning-based algorithm to obtain a measurement matrix for compressive sensing related recovery problems. The focus lies on matrices with a constant modulus constraint which typically represent a network of analog phase…

Signal Processing · Electrical Eng. & Systems 2021-10-15 Michael Koller , Wolfgang Utschick

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme is it decouples the…

Machine Learning · Statistics 2018-06-18 Pratik Jawanpuria , Bamdev Mishra

We describe an efficient FPGA implementation for the exponentiation of large matrices. The research is related to an algorithm for constructing uniformly distributed linear recurring sequences. The design utilizes the special properties of…

Data Structures and Algorithms · Computer Science 2015-03-19 T. Herendi , R. Major

We propose a new layer design by adding a linear gating mechanism to shortcut connections. By using a scalar parameter to control each gate, we provide a way to learn identity mappings by optimizing only one parameter. We build upon the…

Computer Vision and Pattern Recognition · Computer Science 2016-12-30 Pedro H. P. Savarese , Leonardo O. Mazza , Daniel R. Figueiredo

LU-Net is a simple and fast architecture for invertible neural networks (INN) that is based on the factorization of quadratic weight matrices $\mathsf{A=LU}$, where $\mathsf{L}$ is a lower triangular matrix with ones on the diagonal and…

Machine Learning · Computer Science 2023-02-22 Robin Chan , Sarina Penquitt , Hanno Gottschalk

We introduce an information-theoretic framework that views learning as universal prediction under log loss, characterized through regret bounds. Central to the framework is an effective notion of architecture-based model complexity, defined…

Machine Learning · Computer Science 2025-11-04 Meir Feder , Ruediger Urbanke , Yaniv Fogel

Most recent results in matrix completion assume that the matrix under consideration is low-rank or that the columns are in a union of low-rank subspaces. In real-world settings, however, the linear structure underlying these models is…

Machine Learning · Statistics 2015-12-31 Ravi Ganti , Laura Balzano , Rebecca Willett

Recently much attention has been paid to deep generative models, since they have been used to great success for variational inference, generation of complex data types, and more. In most all of these settings, the goal has been to find a…

Machine Learning · Statistics 2019-03-19 Sean R. Bittner , John P. Cunningham

The Lipschitz constant of the map between the input and output space represented by a neural network is a natural metric for assessing the robustness of the model. We present a new method to constrain the Lipschitz constant of dense deep…

Machine Learning · Computer Science 2023-08-22 Ouail Kitouni , Niklas Nolte , Mike Williams

Many types of neural network layers rely on matrix properties such as invertibility or orthogonality. Retaining such properties during optimization with gradient-based stochastic optimizers is a challenging task, which is usually addressed…

Machine Learning · Statistics 2020-12-02 Andreas Krämer , Jonas Köhler , Frank Noé

We propose a novel linear discriminant analysis approach for the classification of high-dimensional matrix-valued data that commonly arises from imaging studies. Motivated by the equivalence of the conventional linear discriminant analysis…

Methodology · Statistics 2019-05-06 Wei Hu , Weining Shen , Hua Zhou , Dehan Kong

We prove that the inverse of a positive-definite matrix can be approximated by a weighted-sum of a small number of matrix exponentials. Combining this with a previous result [OSV12], we establish an equivalence between matrix inversion and…

Data Structures and Algorithms · Computer Science 2016-08-23 Sushant Sachdeva , Nisheeth K. Vishnoi

This work presents a new algorithm to compute the matrix exponential within a given tolerance. Combined with the scaling and squaring procedure, the algorithm incorporates Taylor, partitioned and classical Pad\'e methods shown to be…

Numerical Analysis · Mathematics 2024-04-22 Sergio Blanes , Nikita Kopylov , Muaz Seydaoğlu

Integer quantization has emerged as a critical technique to facilitate deployment on resource-constrained devices. Although they do reduce the complexity of the learning models, their inference performance is often prone to…

Machine Learning · Computer Science 2025-05-22 Duncan Bart , Bruno Endres Forlin , Ana-Lucia Varbanescu , Marco Ottavi , Kuan-Hsun Chen

This paper studies inference in linear models with a high-dimensional parameter matrix that can be well-approximated by a ``spiked low-rank matrix.'' A spiked low-rank matrix has rank that grows slowly compared to its dimensions and nonzero…

Statistics Theory · Mathematics 2023-01-04 Victor Chernozhukov , Christian Hansen , Yuan Liao , Yinchu Zhu

Many current approaches to machine learning in particle physics use generic architectures that require large numbers of parameters and disregard underlying physics principles, limiting their applicability as scientific modeling tools. In…

High Energy Physics - Phenomenology · Physics 2022-12-27 Alexander Bogatskiy , Timothy Hoffman , David W. Miller , Jan T. Offermann

In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-of-the-art framework that depends upon few hyper parameters…

Computer Vision and Pattern Recognition · Computer Science 2017-03-07 Edouard Oyallon

Automated per-instance algorithm selection and configuration have shown promising performances for a number of classic optimization problems, including satisfiability, AI planning, and TSP. The techniques often rely on a set of features…

Neural and Evolutionary Computing · Computer Science 2020-10-01 Tome Eftimov , Gorjan Popovski , Quentin Renau , Peter Korosec , Carola Doerr
‹ Prev 1 2 3 10 Next ›