activity
20162018
most citedRecovery Guarantee of Non-negative Matrix Factorization via Alternating Updates

16 citations · 17 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2018

Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data

Yuanzhi Li, Yingyu Liang

Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-laye…

cs.LG2018

Learning Mixtures of Linear Regressions with Nearly Optimal Complexity

Yuanzhi Li, Yingyu Liang

Mixtures of Linear Regressions (MLR) is an important mixture model with many applications. In this model, each observation is generated from one of the several unknown linear regre…

cs.LG2017

Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations

Yuanzhi Li, Yingyu Liang

Non-negative matrix factorization is a basic tool for decomposing data into the feature and weight matrices under non-negativity constraints, and in practice is often solved in the…

cs.LG2016★ 16 cited

Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates

Yuanzhi Li, Yingyu Liang, Andrej Risteski

Non-negative matrix factorization is a popular tool for decomposing data into feature and weight matrices under non-negativity constraints. It enjoys practical success but is poorl…

cs.LG2016★ 1 cited

Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods

Yuanzhi Li, Andrej Risteski

The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family, has bee…