Sparse and spurious: dictionary learning with noise and outliers
arXiv:1407.5155
Abstract
A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only been a few theoretical arguments supporting these evidences. In particular, sparse coding, or sparse dictionary learning, relies on a non-convex procedure whose local minima have not been fully analyzed yet. In this paper, we consider a probabilistic model of sparse signals, and show that, with high probability, sparse coding admits a local minimum around the reference dictionary generating the signals. Our study takes into account the case of over-complete dictionaries, noisy signals, and possible outliers, thus extending previous work limited to noiseless settings and/or under-complete dictionaries. The analysis we conduct is non-asymptotic and makes it possible to understand how the key quantities of the problem, such as the coherence or the level of noise, can scale with respect to the dimension of the signals, the number of atoms, the sparsity and the number of observations.
arXiv commentThis is a substantially revised version of a first draft that appeared as a preprint titled "Local stability and robustness of sparse dictionary learning in the presence of noise", http://hal.inria.fr/hal-00737152, IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers (IEEE), 2015, pp.22
References in corpus (10)
- Spike and slab variable selection: Frequentist and Bayesian strategies
- On the conditions used to prove oracle results for the Lasso
- Proximal Methods for Hierarchical Sparse Coding
- Convex Sparse Matrix Factorizations
- On the Identifiability of Overcomplete Dictionaries via the Minimisation Principle Underlying K-SVD
- The Sample Complexity of Dictionary Learning
- On the Local Correctness of L^1 Minimization for Dictionary Learning
- Local stability and robustness of sparse dictionary learning in the presence of noise
- On the Sample Complexity of Predictive Sparse Coding
- Performance Limits of Dictionary Learning for Sparse Coding