Dictionary Learning

151 papers with code • 0 benchmarks • 6 datasets

Dictionary Learning is an important problem in multiple areas, ranging from computational neuroscience, machine learning, to computer vision and image processing. The general goal is to find a good basis for given data. More formally, in the Dictionary Learning problem, also known as sparse coding, we are given samples of a random vector $y\in\mathbb{R}^n$, of the form $y=Ax$ where $A$ is some unknown matrix in $\mathbb{R}^{n×m}$, called dictionary, and $x$ is sampled from an unknown distribution over sparse vectors. The goal is to approximately recover the dictionary $A$.

Source: Polynomial-time tensor decompositions with sum-of-squares

Libraries

Use these libraries to find Dictionary Learning models and implementations

Latest papers with no code

Image Deraining via Self-supervised Reinforcement Learning

no code yet • 27 Mar 2024

The work aims to recover rain images by removing rain streaks via Self-supervised Reinforcement Learning (RL) for image deraining (SRL-Derain).

Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies

no code yet • 22 Mar 2024

Optimal control of parametric partial differential equations (PDEs) is crucial in many applications in engineering and science.

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

no code yet • 19 Feb 2024

Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations.

An SVD-free Approach to Nonlinear Dictionary Learning based on RVFL

no code yet • 6 Feb 2024

The proposed RVFL-based nonlinear Dictionary Learning (RVFLDL) learns a dictionary as a sparse-to-dense feature map from nonlinear sparse coefficients to the dense input features.

Learning a Gaussian Mixture for Sparsity Regularization in Inverse Problems

no code yet • 29 Jan 2024

In inverse problems, it is widely recognized that the incorporation of a sparsity prior yields a regularization effect on the solution.

Convergence and complexity of block majorization-minimization for constrained block-Riemannian optimization

no code yet • 16 Dec 2023

Block majorization-minimization (BMM) is a simple iterative algorithm for nonconvex optimization that sequentially minimizes a majorizing surrogate of the objective function in each block coordinate while the other block coordinates are held fixed.

Learning Interpretable Queries for Explainable Image Classification with Information Pursuit

no code yet • 16 Dec 2023

To solve the optimization problem, we propose a new query dictionary learning algorithm inspired by classical sparse dictionary learning.

Explainable Trajectory Representation through Dictionary Learning

no code yet • 13 Dec 2023

A hierarchical dictionary learning scheme is also proposed to ensure the algorithm's scalability on large networks, leading to a multi-scale trajectory representation.

Clustering Inductive Biases with Unrolled Networks

no code yet • 30 Nov 2023

We propose an autoencoder architecture (WLSC) whose latent representations are implicitly, locally organized for spectral clustering through a Laplacian quadratic form of a bipartite graph, which generates a diverse set of artificial receptive fields that match primate data in V1 as faithfully as recent contrastive frameworks like Local Low Dimensionality, or LLD \citep{lld} that discard sparse dictionary learning.

SenseAI: Real-Time Inpainting for Electron Microscopy

no code yet • 25 Nov 2023

Despite their proven success and broad applicability to Electron Microscopy (EM) data, joint dictionary-learning and sparse-coding based inpainting algorithms have so far remained impractical for real-time usage with an Electron Microscope.