252 citations · 3.3k across the 92 of their papers we have counts for
9 papers · 1 filter
Provable learning of Noisy-or Networks
Sanjeev Arora, Rong Ge, Tengyu Ma +1
Many machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a prob…
Identity Matters in Deep Learning
Moritz Hardt, Tengyu Ma
An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not onl…
Finding Approximate Local Minima Faster than Gradient Descent
Naman Agarwal, Zeyuan Allen-Zhu, Brian Bullins +2
We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and t…
Polynomial-time Tensor Decompositions with Sum-of-Squares
Tengyu Ma, Jonathan Shi, David Steurer
We give new algorithms based on the sum-of-squares method for tensor decomposition. Our results improve the best known running times from quasi-polynomial to polynomial for several…
A Non-generative Framework and Convex Relaxations for Unsupervised Learning
Elad Hazan, Tengyu Ma
We give a novel formal theoretical framework for unsupervised learning with two distinctive characteristics. First, it does not assume any generative model and based on a worst-cas…
Gradient Descent Learns Linear Dynamical Systems
Moritz Hardt, Tengyu Ma, Benjamin Recht
We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system fro…
Provable Algorithms for Inference in Topic Models
Sanjeev Arora, Rong Ge, Frederic Koehler +2
Recently, there has been considerable progress on designing algorithms with provable guarantees -- typically using linear algebraic methods -- for parameter learning in latent vari…
Matrix Completion has No Spurious Local Minimum
Rong Ge, Jason D. Lee, Tengyu Ma
Matrix completion is a basic machine learning problem that has wide applications, especially in collaborative filtering and recommender systems. Simple non-convex optimization algo…
Linear Algebraic Structure of Word Senses, with Applications to Polysemy
Sanjeev Arora, Yuanzhi Li, Yingyu Liang +2
Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses resid…