English
Related papers

Related papers: Generative modeling of Sparse Approximate Inverse …

200 papers

Nonnegative matrix factorization (NMF) under the separability assumption can provably be solved efficiently, even in the presence of noise, and has been shown to be a powerful technique in document classification and hyperspectral unmixing.…

Machine Learning · Statistics 2015-04-02 Nicolas Gillis , Stephen A. Vavasis

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Machine Learning · Computer Science 2026-03-17 Thibault Formal , Maxime Louis , Hervé Dejean , Stéphane Clinchant

A linearly implicit conservative difference scheme is applied to discretize the attractive coupled nonlinear Schr\"odinger equations with fractional Laplacian. Complex symmetric linear systems can be obtained, and the system matrices are…

Numerical Analysis · Mathematics 2023-10-19 Yan Cheng , Xi Yang

We provide a comparative study of the Subspace Projected Approximate Matrix method, abbreviated SPAM, which is a fairly recent iterative method to compute a few eigenvalues of a Hermitian matrix $A$. It falls in the category of inner-outer…

Numerical Analysis · Mathematics 2011-03-10 Jan H. Brandts , Ricardo Reis da Silva

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper…

Machine Learning · Computer Science 2025-07-18 Nikita Koriagin , Yaroslav Aksenov , Daniil Laptev , Gleb Gerasimov , Nikita Balagansky , Daniil Gavrilov

This article introduces a general purpose framework and software to approximate partial differential equations (PDEs). The sparsity patterns of finite element discretized operators is identified automatically using the tools from…

Numerical Analysis · Mathematics 2024-10-17 Kiefer Green , Harbir Antil

Domain decomposition (DD) methods are widely used as preconditioner techniques. Their effectiveness relies on the choice of a locally constructed coarse space. Thus far, this construction was mostly achieved using non-assembled matrices…

Numerical Analysis · Mathematics 2021-09-14 Hussam Al Daas , Pierre Jolivet

We develop a stochastic algorithm for independent component analysis that incorporates multi-trial supervision, which is available in many scientific contexts. The method blends a proximal gradient-type algorithm in the space of invertible…

Machine Learning · Computer Science 2025-08-29 Ronak Mehta , Mateus Piovezan Otto , Noah Stanis , Azadeh Yazdan-Shahmorad , Zaid Harchaoui

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks. Initial algorithms…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Jakob Geusen , Gustav Bredell , Tianfei Zhou , Ender Konukoglu

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our…

Machine Learning · Computer Science 2015-06-08 Mathieu Germain , Karol Gregor , Iain Murray , Hugo Larochelle

We present a novel approach to system identification (SI) using deep learning techniques. Focusing on parametric system identification (PSI), we use a supervised learning approach for estimating the parameters of discrete and…

Systems and Control · Electrical Eng. & Systems 2023-06-21 Connor James Stephens , Emmanuel Blazquez

In this paper, we estimate the high dimensional precision matrix under the weak sparsity condition where many entries are nearly zero. We revisit the sparse column-wise inverse operator (SCIO) estimator \cite{liu2015fast} and derive its…

Statistics Theory · Mathematics 2022-10-21 Zeyu Wu , Cheng Wang , Weidong Liu

Structured prediction requires searching over a combinatorial number of structures. To tackle it, we introduce SparseMAP: a new method for sparse structured inference, and its natural loss function. SparseMAP automatically selects only a…

Machine Learning · Statistics 2018-06-21 Vlad Niculae , André F. T. Martins , Mathieu Blondel , Claire Cardie

We propose a new algorithm for the fast solution of large, sparse, symmetric positive-definite linear systems, spaND -- sparsified Nested Dissection. It is based on nested dissection, sparsification and low-rank compression. After…

Numerical Analysis · Mathematics 2020-01-28 Léopold Cambier , Chao Chen , Erik G Boman , Sivasankaran Rajamanickam , Raymond S. Tuminaro , Eric Darve

Thus far, sparse representations have been exploited largely in the context of robustly estimating functions in a noisy environment from a few measurements. In this context, the existence of a basis in which the signal class under…

Data Structures and Algorithms · Computer Science 2009-06-26 Mohamed-Ali Belabbas , Patrick J. Wolfe

Despite its nonconvex nature, $\ell_0$ sparse approximation is desirable in many theoretical and application cases. We study the $\ell_0$ sparse approximation problem with the tool of deep learning, by proposing Deep $\ell_0$ Encoders. Two…

Machine Learning · Computer Science 2015-11-24 Zhangyang Wang , Qing Ling , Thomas S. Huang

Inducing-point-based sparse variational Gaussian processes have become the standard workhorse for scaling up GP models. Recent advances show that these methods can be improved by introducing a diagonal scaling matrix to the conditional…

Machine Learning · Statistics 2025-07-04 Thang D. Bui , Michalis K. Titsias

Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization…

Computation and Language · Computer Science 2018-09-05 Vlad Niculae , André F. T. Martins , Claire Cardie

Model selection in machine learning (ML) is a crucial part of the Bayesian learning procedure. Model choice may impose strong biases on the resulting predictions, which can hinder the performance of methods such as Bayesian neural networks…

Machine Learning · Statistics 2022-08-09 Simón Rodríguez Santana , Luis A. Ortega , Daniel Hernández-Lobato , Bryan Zaldívar