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 2018Show all

12 papers · 1 filter

math.OC2018

Solving Non-Convex Non-Concave Min-Max Games Under Polyak-Łojasiewicz Condition

Maziar Sanjabi, Meisam Razaviyayn, Jason D. Lee

In this short note, we consider the problem of solving a min-max zero-sum game. This problem has been extensively studied in the convex-concave regime where the global solution can…

cs.LG2018

Gradient Descent Finds Global Minima of Deep Neural Networks

Simon S. Du, Jason D. Lee, Haochuan Li +2

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero tr…

stat.ML2018

Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel

Colin Wei, Jason D. Lee, Qiang Liu +1

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the…

math.OC2018

Convergence to Second-Order Stationarity for Constrained Non-Convex Optimization

Maher Nouiehed, Jason D. Lee, Meisam Razaviyayn

We consider the problem of finding an approximate second-order stationary point of a constrained non-convex optimization problem. We first show that, unlike the gradient descent me…

math.OC2018

Provably Correct Automatic Subdifferentiation for Qualified Programs

Sham Kakade, Jason D. Lee

The Cheap Gradient Principle (Griewank 2008) --- the computational cost of computing the gradient of a scalar-valued function is nearly the same (often within a factor of ) as t…

cs.LG2018

Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced

Simon S. Du, Wei Hu, Jason D. Lee

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural…