132 citations · 344 across the 10 of their papers we have counts for
10 papers
Spectral Learning on Matrices and Tensors
Majid Janzamin, Rong Ge, Jean Kossaifi +1
Spectral methods have been the mainstay in several domains such as machine learning and scientific computing. They involve finding a certain kind of spectral decomposition to obtai…
Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods
Majid Janzamin, Hanie Sedghi, Anima Anandkumar
Training neural networks is a challenging non-convex optimization problem, and backpropagation or gradient descent can get stuck in spurious local optima. We propose a novel algori…
Score Function Features for Discriminative Learning: Matrix and Tensor Framework
Majid Janzamin, Hanie Sedghi, Anima Anandkumar
Feature learning forms the cornerstone for tackling challenging learning problems in domains such as speech, computer vision and natural language processing. In this paper, we cons…
Score Function Features for Discriminative Learning
Majid Janzamin, Hanie Sedghi, Anima Anandkumar
Feature learning forms the cornerstone for tackling challenging learning problems in domains such as speech, computer vision and natural language processing. In this paper, we cons…
Analyzing Tensor Power Method Dynamics in Overcomplete Regime
Anima Anandkumar, Rong Ge, Majid Janzamin
We present a novel analysis of the dynamics of tensor power iterations in the overcomplete regime where the tensor CP rank is larger than the input dimension. Finding the CP decomp…
Sample Complexity Analysis for Learning Overcomplete Latent Variable Models through Tensor Methods
Animashree Anandkumar, Rong Ge, Majid Janzamin
We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionalit…
Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank- Updates
Animashree Anandkumar, Rong Ge, Majid Janzamin
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 simple al…
When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity
Animashree Anandkumar, Daniel Hsu, Majid Janzamin +1
Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified…
High-Dimensional Covariance Decomposition into Sparse Markov and Independence Models
Majid Janzamin, Animashree Anandkumar
Fitting high-dimensional data involves a delicate tradeoff between faithful representation and the use of sparse models. Too often, sparsity assumptions on the fitted model are too…
High-Dimensional Covariance Decomposition into Sparse Markov and Independence Domains
Majid Janzamin, Animashree Anandkumar
In this paper, we present a novel framework incorporating a combination of sparse models in different domains. We posit the observed data as generated from a linear combination of…