Exact Recovery of Sparsely Used Overcomplete Dictionaries
By Alekh Agarwal, Anima Anandkumar, Praneeth Netrapalli. 2013
58 citations recorded by the source corpus.
Subfields: Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Representation & Self-Supervised Learning
- Sanjeev Arora
- Rong Ge
- Ankur Moitra
- Karin Schnass
- Anima Anandkumar
- Tengyu Ma
- Prateek Jain
- Praneeth Netrapalli
Citations in the corpus
- A Geometric Analysis of Phase Retrieval (2016, background): “Accordingly, the di for i ∈ [4] in Propositions 11– 14 are changed to di −ε, with other conditions unaltered.”
- On the Identifiability of Overcomplete Dictionaries via the Minimisation Principle Underlying K-SVD (2013, methodology): “not be guaranteed to converge to a local minimiser 1. For the sake of completeness we also mention (without discussion) some very recent results, developed while this work has been under review, [5], [2], [1] . April 3, 2015 DRAFT 5 of (1) unless S= 1 and a greedy algorithm is used, see also the dis”
- Simple, Efficient, and Neural Algorithms for Sparse Coding (2015, methodology): “Arora et al. (2014) and Agarwal et al. (2013, 2014) independently gave algorithms in the overcomplete case assuming that A ∗ is µ -incoherent (which we define in the next section).”
- Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization (2013, methodology): “The problem of sparse coding consists of unsupervised learning of the dictionary and the coefficient matrices.”
- New Algorithms for Learning Incoherent and Overcomplete Dictionaries (2013, methodology): “Their second [1] gives an algorithm –a version of alternating minimization– that converges to the correct dictionary given a good initial dictionary (such a good initialization can only be found using [2] in special cases, or more generally using this paper).”
- Complete dictionary recovery over the sphere (2015, methodology): “[9, 10] and [11, 12] have subsequently given efficient algorithms for the overcomplete setting (m ≥ n), based on a combination of {clustering or spectral initialization} and local refinement.”