273 citations · 1.6k across the 53 of their papers we have counts for
9 papers · 1 filter
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit w…
Recovery Guarantees for Quadratic Tensors with Sparse Observations
Hongyang R. Zhang, Vatsal Sharan, Moses Charikar +1
We consider the tensor completion problem of predicting the missing entries of a tensor. The commonly used CP model has a triple product form, but an alternate family of quadratic…
Generalizing Word Embeddings using Bag of Subwords
Jinman Zhao, Sidharth Mudgal, Yingyu Liang
We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word…
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…
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
Shengchao Liu, Mehmet Furkan Demirel, Yingyu Liang
Machine learning techniques have recently been adopted in various applications in medicine, biology, chemistry, and material engineering. An important task is to predict the proper…
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors
Mikhail Khodak, Nikunj Saunshi, Yingyu Liang +3
Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textua…
Domain Adapted Word Embeddings for Improved Sentiment Classification
Prathusha K Sarma, YIngyu Liang, William A Sethares
Generic word embeddings are trained on large-scale generic corpora; Domain Specific (DS) word embeddings are trained only on data from a domain of interest. This paper proposes a m…
Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
Jiefeng Chen, Xi Wu, Vaibhav Rastogi +2
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such a…
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…