On the Sample Complexity of Predictive Sparse Coding

  title={On the Sample Complexity of Predictive Sparse Coding},
  author={Nishant A. Mehta and Alexander G. Gray},
Predictive sparse coding algorithms recently have demonstrated impressive performance on a variety of supervised tasks, but they lack a learning theoretic analysis. We establish the first generalization bounds for predictive sparse coding. In the overcomplete dictionary learning setting, where the dictionary size k exceeds the dimensionality d of the data, we present an estimation error bound that is roughly O( √ dk/m + √ s/(μm)). In the infinite-dimensional setting, we show a dimension-free… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 1 time. VIEW TWEETS

From This Paper

Topics from this paper.


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 23 references

On the Importance of Small Coordinate Projections

Journal of Machine Learning Research • 2004
View 4 Excerpts
Highly Influenced

On the LASSO and Dantzig selector equivalence

2010 44th Annual Conference on Information Sciences and Systems (CISS) • 2010
View 4 Excerpts
Highly Influenced

Differentiable Sparse Coding

View 4 Excerpts
Highly Influenced

Learning and Generalization with Applications to Neural Networks

M. Vidyasagar
View 1 Excerpt
Highly Influenced

Stability of the solution of definite quadratic programs

James W. Daniel
Mathematical Programming, • 1973
View 3 Excerpts
Highly Influenced

Task-Driven Dictionary Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2012
View 3 Excerpts

Similar Papers

Loading similar papers…