Lenka who will be at our next Paris Machine Learning meetup on June 8th, was recently speaking at the Simons institute's Random Instances and Phase Transitions workshop within the trimester long Counting Complexity and Phase Transitions program. Here is Solvable Model of Unsupervised Feature Learning by Lenka Zdeborova,
We introduce factorization of certain randomly generated matrices as a probabilistic model for unsupervised feature learning. Using the replica method we obtain an exact closed formula for the minimum mean-squared error and sample complexity for reconstruction of the features from data. An alternative way to derive this formula is via state evolution of the associated approximate message passing. Analyzing the fixed points of this formula we identify a gap between computationally tractable and information theoretically optimal inference, associated to a first order phase transition. The model can serve for benchmarking generic-purpose feature learning algorithms, its analysis provides insight into theoretical understanding of unsupervised learning from data.
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.
No comments:
Post a Comment