Online and Differentially-Private Tensor Decomposition
نویسندگان
چکیده
Tensor decomposition is an important tool for big data analysis. In this paper,we resolve many of the key algorithmic questions regarding robustness, memoryefficiency, and differential privacy of tensor decomposition. We propose simplevariants of the tensor power method which enjoy these strong properties. We presentthe first guarantees for online tensor power method which has a linear memoryrequirement. Moreover, we present a noise calibrated tensor power method withefficient privacy guarantees. At the heart of all these guarantees lies a carefulperturbation analysis derived in this paper which improves up on the existingresults significantly.
منابع مشابه
Differentially-Private Orthogonal Tensor Decomposition
Differential privacy has recently received a significant amount of research attention for its robustness against known attacks. Decomposition of tensors has applications in many areas including signal processing, machine learning, computer vision and neuroscience. In this paper, we particularly focus on differentially-private orthogonal decomposition of symmetric tensors that arise in several l...
متن کاملA simple form of MT impedance tensor analysis to simplify its decomposition to remove the effects of near surface small-scale 3-D conductivity structures
Magnetotelluric (MT) is a natural electromagnetic (EM) technique which is used for geothermal, petroleum, geotechnical, groundwater and mineral exploration. MT is also routinely used for mapping of deep subsurface structures. In this method, the measured regional complex impedance tensor (Z) is substantially distorted by any topographical feature or small-scale near-surface, three-dimensional (...
متن کاملDifferentially Private Local Electricity Markets
Privacy-preserving electricity markets have a key role in steering customers towards participation in local electricity markets by guarantying to protect their sensitive information. Moreover, these markets make it possible to statically release and share the market outputs for social good. This paper aims to design a market for local energy communities by implementing Differential Privacy (DP)...
متن کاملFast online low-rank tensor subspace tracking by CP decomposition using recursive least squares from incomplete observations
We consider the problem of online subspace tracking of a partially observed high-dimensional data stream corrupted by noise, where we assume that the data lie in a low-dimensional linear subspace. This problem is cast as an online low-rank tensor completion problem. We propose a novel online tensor subspace tracking algorithm based on the CANDECOMP/PARAFAC (CP) decomposition, dubbed OnLine Low-...
متن کاملEscaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition
We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points. In this paper we identify strict saddle property for non-convex problem that allows for efficient optimization. Using this property we show that from an arbit...
متن کامل