no code implementations • 16 Apr 2020 • Majid Janzamin, Rong Ge, Jean Kossaifi, Anima Anandkumar
PCA and other spectral techniques applied to matrices have several limitations.
no code implementations • 28 Jun 2015 • Majid Janzamin, Hanie Sedghi, Anima Anandkumar
We propose a novel algorithm based on tensor decomposition for guaranteed training of two-layer neural networks.
no code implementations • 19 Dec 2014 • Majid Janzamin, Hanie Sedghi, Anima Anandkumar
In this paper, we consider a novel class of matrix and tensor-valued features, which can be pre-trained using unlabeled samples.
no code implementations • 9 Dec 2014 • Majid Janzamin, Hanie Sedghi, Anima Anandkumar
In this paper, we consider a novel class of matrix and tensor-valued features, which can be pre-trained using unlabeled samples.
no code implementations • 9 Dec 2014 • Hanie Sedghi, Majid Janzamin, Anima Anandkumar
In contrast, we present a tensor decomposition method which is guaranteed to correctly recover the parameters.
no code implementations • 6 Nov 2014 • 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.
no code implementations • 3 Aug 2014 • Animashree Anandkumar, Rong Ge, Majid Janzamin
In the unsupervised setting, we use a simple initialization algorithm based on SVD of the tensor slices, and provide guarantees under the stricter condition that $k\le \beta d$ (where constant $\beta$ can be larger than $1$), where the tensor method recovers the components under a polynomial running time (and exponential in $\beta$).
no code implementations • 21 Feb 2014 • Animashree Anandkumar, Rong Ge, Majid Janzamin
In this paper, we provide local and global convergence guarantees for recovering CP (Candecomp/Parafac) tensor decomposition.
no code implementations • NeurIPS 2013 • Animashree Anandkumar, Daniel Hsu, Majid Janzamin, Sham Kakade
This set of higher-order expansion conditions allow for overcomplete models, and require the existence of a perfect matching from latent topics to higher order observed words.
no code implementations • 5 Nov 2012 • Majid Janzamin, Animashree Anandkumar
Fitting high-dimensional data involves a delicate tradeoff between faithful representation and the use of sparse models.