On the Optimization Landscape of Tensor Decompositions

Authors: Rong Ge, Tengyu Ma

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we analyze the optimization landscape of the random over-complete tensor decomposition problem, which has many applications in unsupervised leaning, especially in learning latent variable models. We show that for any small constant ε > 0, among the set of points with function values (1 + ε)-factor larger than the expectation of the function, all the local maxima are approximate global maxima. Our main technique uses Kac-Rice formula and random matrix theory.
Researcher Affiliation Collaboration Rong Ge Duke University rongge@cs.duke.edu Tengyu Ma Facebook AI Research tengyuma@cs.stanford.edu
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statements about the availability of source code, nor does it include a link to a code repository.
Open Datasets No The paper describes a theoretical model where 'vectors ai Rd are assumed to be drawn i.i.d from Gaussian distribution N(0, I),' rather than using a publicly available dataset for training.
Dataset Splits No The paper is theoretical and does not describe empirical experiments involving dataset splits (training, validation, test).
Hardware Specification No The paper is theoretical and does not describe any computational experiments or hardware used.
Software Dependencies No The paper is theoretical and does not mention any software dependencies with specific version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameters or training configurations.