Skip to yearly menu bar Skip to main content


A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing

Ming Lin · Jieping Ye

Area 5+6+7+8 #121

Keywords: [ Similarity and Distance Learning ] [ Large Scale Learning and Big Data ] [ Matrix Factorization ] [ Online Learning ]

Abstract: We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sampled from $d$ dimensional random Gaussian vectors and the target second order coefficient matrix in gFM is of rank $k$, our algorithm converges linearly, achieves $O(\epsilon)$ recovery error after retrieving $O(k^{3}d\log(1/\epsilon))$ training instances, consumes $O(kd)$ memory in one-pass of dataset and only requires matrix-vector product operations in each iteration. The key ingredient of our framework is a construction of an estimation sequence endowed with a so-called Conditionally Independent RIP condition (CI-RIP). As special cases of gFM, our framework can be applied to symmetric or asymmetric rank-one matrix sensing problems, such as inductive matrix completion and phase retrieval.

Live content is unavailable. Log in and register to view live content