SOTAVerified

Dictionary Learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 823 papers

TitleStatusHype
Joint space-time wind field data extrapolation and uncertainty quantification using nonparametric Bayesian dictionary learning—0
Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix FactorizationCode1
Evaluating Sparse Autoencoders: From Shallow Design to Matching Pursuit—0
Mechanistic Decomposition of Sentence Representations—0
HyperSteer: Activation Steering at Scale with HypernetworksCode2
Interpreting Large Text-to-Image Diffusion Models with Dictionary LearningCode0
Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions—0
DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding SpacesCode1
Modeling Musical Genre Trajectories through Pathlet LearningCode0
From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models—0
Towards Understanding the Nature of Attention with Low-Rank Sparse DecompositionCode1
Optimizing Hard Thresholding for Sparse Model Discovery—0
Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language Models—0
Recognition of Geometrical Shapes by Dictionary Learning—0
Mixture-of-Shape-Experts (MoSE): End-to-End Shape Dictionary Framework to Prompt SAM for Generalizable Medical Segmentation—0
Koopman-Based Methods for EV Climate Dynamics: Comparing eDMD Approaches—0
Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation—0
Topological Dictionary LearningCode0
Sparse Dictionary Learning for Image Recovery by Iterative Shrinkage—0
Online multidimensional dictionary learning—0
Weakly Supervised Convolutional Dictionary Learning for Multi-Label ClassificationCode0
Personalized Convolutional Dictionary Learning of Physiological Time SeriesCode0
Dynamic Dictionary Learning for Remote Sensing Image SegmentationCode1
Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts—0
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models—0
Show:102550
← PrevPage 1 of 33Next →

No leaderboard results yet.