Escaping 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 …
for non-convex functions the goal is to find a reasonable local minimum, and the main …
Tensors for data mining and data fusion: Models, applications, and scalable algorithms
EE Papalexakis, C Faloutsos… - ACM Transactions on …, 2016 - dl.acm.org
Tensors and tensor decompositions are very powerful and versatile tools that can model a
wide variety of heterogeneous, multiaspect data. As a result, tensor decompositions, which …
wide variety of heterogeneous, multiaspect data. As a result, tensor decompositions, which …
Tensor completion algorithms in big data analytics
Tensor completion is a problem of filling the missing or unobserved entries of partially
observed tensors. Due to the multidimensional character of tensors in describing complex …
observed tensors. Due to the multidimensional character of tensors in describing complex …
Navigating the local modes of big data
Each day humans generate massive volumes of data in a variety of different forms (Lazer et
al., 2009). For example, digitized texts provide a rich source of political content through …
al., 2009). For example, digitized texts provide a rich source of political content through …
Fast and guaranteed tensor decomposition via sketching
Abstract Tensor CANDECOMP/PARAFAC (CP) decomposition has wide applications in
statistical learning of latent variable models and in data mining. In this paper, we propose …
statistical learning of latent variable models and in data mining. In this paper, we propose …
[PDF][PDF] A tensor approach to learning mixed membership community models
Community detection is the task of detecting hidden communities from observed
interactions. Guaranteed community detection has so far been mostly limited to models with …
interactions. Guaranteed community detection has so far been mostly limited to models with …
Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank- Updates
In this paper, we provide local and global convergence guarantees for recovering CP
(Candecomp/Parafac) tensor decomposition. The main step of the proposed algorithm is a …
(Candecomp/Parafac) tensor decomposition. The main step of the proposed algorithm is a …
A tensor spectral approach to learning mixed membership community models
Modeling community formation and detecting hidden communities in networks is a well
studied problem. However, theoretical analysis of community detection has been mostly …
studied problem. However, theoretical analysis of community detection has been mostly …
Streaming graph challenge: Stochastic block partition
E Kao, V Gadepally, M Hurley, M Jones… - 2017 IEEE High …, 2017 - ieeexplore.ieee.org
An important objective for analyzing real-world graphs is to achieve scalable performance
on large, streaming graphs. A challenging and relevant example is the graph partition …
on large, streaming graphs. A challenging and relevant example is the graph partition …
Tensor factorization via matrix factorization
V Kuleshov, A Chaganty… - Artificial Intelligence and …, 2015 - proceedings.mlr.press
Tensor factorization arises in many machine learning applications, such as knowledge base
modeling and parameter estimation in latent variable models. However, numerical methods …
modeling and parameter estimation in latent variable models. However, numerical methods …