activity
20152023
most citedLearning One-hidden-layer Neural Networks with Landscape Design

112 citations · 288 across the 11 of their papers we have counts for

collaborators
Showing 2019Show all

9 papers · 1 filter

cs.LG20198 cited

When Does Non-Orthogonal Tensor Decomposition Have No Spurious Local Minima?

Maziar Sanjabi, Sina Baharlouei, Meisam Razaviyayn +1

We study the optimization problem for decomposing dimensional fourth-order Tensors with non-orthogonal components. We derive \textit{deterministic} conditions under which s…

cs.LG2019

SGD Learns One-Layer Networks in WGANs

Qi Lei, Jason D. Lee, Alexandros G. Dimakis +1

Generative adversarial networks (GANs) are a widely used framework for learning generative models. Wasserstein GANs (WGANs), one of the most successful variants of GANs, require so…

cs.LG201913 cited

Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks

Yu Bai, Jason D. Lee

Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs). NTK theory leads t…

cs.LG2019

Optimal transport mapping via input convex neural networks

Ashok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh +1

In this paper, we present a novel and principled approach to learn the optimal transport between two distributions, from samples. Guided by the optimal transport theory, we learn t…

cs.LG2019

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift

Alekh Agarwal, Sham M. Kakade, Jason D. Lee +1

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about ev…

cs.LG2019

Convergence of Adversarial Training in Overparametrized Neural Networks

Ruiqi Gao, Tianle Cai, Haochuan Li +3

Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial tr…