activity
20172020
most citedGeneralization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints

53 citations · 73 across the 3 of their papers we have counts for

collaborators

8 papers

cs.GR202013 cited

SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors

Mohammad Keshavarzi, Aakash Parikh, Xiyu Zhai +3

Spatial computing experiences are constrained by the real-world surroundings of the user. In such experiences, augmenting virtual objects to existing scenes require a contextual ap…

math.ST2019

On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels

Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai

We study the risk of minimum-norm interpolants of data in Reproducing Kernel Hilbert Spaces. Our upper bounds on the risk are of a multiple-descent shape for the various scalings o…

cs.LG2019

Near Optimal Stratified Sampling

Tiancheng Yu, Xiyu Zhai, Suvrit Sra

The performance of a machine learning system is usually evaluated by using i.i.d.\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaini…

stat.ML20187 cited

Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon

Alexander Rakhlin, Xiyu Zhai

We show that minimum-norm interpolation in the Reproducing Kernel Hilbert Space corresponding to the Laplace kernel is not consistent if input dimension is constant. The lower boun…

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…

cs.LG2018

Gradient Descent Provably Optimizes Over-parameterized Neural Networks

Simon S. Du, Xiyu Zhai, Barnabas Poczos +1

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective fu…