Survey on Algorithms for multi-index models
By: Joan Bruna, Daniel Hsu
Potential Business Impact:
Finds patterns faster in big data.
We review the literature on algorithms for estimating the index space in a multi-index model. The primary focus is on computationally efficient (polynomial-time) algorithms in Gaussian space, the assumptions under which consistency is guaranteed by these methods, and their sample complexity. In many cases, a gap is observed between the sample complexity of the best known computationally efficient methods and the information-theoretical minimum. We also review algorithms based on estimating the span of gradients using nonparametric methods, and algorithms based on fitting neural networks using gradient descent
Similar Papers
Computational lower bounds in latent models: clustering, sparse-clustering, biclustering
Statistics Theory
Finds limits of computer problem-solving abilities.
Optimality and computational barriers in variable selection under dependence
Statistics Theory
Finds the best way to pick important data.
Learning single-index models via harmonic decomposition
Machine Learning (CS)
Finds hidden patterns in data by looking from all sides.