Timezone: »

Linear-Sample Learning of Low-Rank Distributions
Ayush Jain · Alon Orlitsky

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1251
Many latent-variable applications, including community detection, collaborative filtering, genomic analysis, and NLP, model data as generated by low-rank matrices. Yet despite considerable research, except for very special cases, the number of samples required to efficiently recover the underlying matrices has not been known. We determine the onset of learning in several common latent-variable settings. For all of them, we show that learning $k\times k$, rank-$r$, matrices to normalized $L_1$ distance $\epsilon$ requires $\Omega(\frac{kr}{\epsilon^2})$ samples, and propose an algorithm that uses ${\cal O}(\frac{kr}{\epsilon^2}\log^2\frac r\epsilon)$ samples, a number linear in the high dimension, and nearly linear in the, typically low, rank. The algorithm improves on existing spectral techniques and runs in polynomial time. The proofs establish new results on the rapid convergence of the spectral distance between the model and observation matrices, and may be of independent interest.

Author Information

Ayush Jain (UC San Diego)
Alon Orlitsky (University of California, San Diego)

More from the Same Authors