activity
20192026
most citedTackling the Curse of Dimensionality with Physics-Informed Neural Networks

166 citations · 489 across the 33 of their papers we have counts for

collaborators
Showing stat.MLShow all

6 papers · 1 filter

stat.ML2022★ 3 cited

TuneUp: A Simple Improved Training Strategy for Graph Neural Networks

Weihua Hu, Kaidi Cao, Kexin Huang +4

Despite recent advances in Graph Neural Networks (GNNs), their training strategies remain largely under-explored. The conventional training strategy learns over all nodes in the or…

stat.ML2019

Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes

Kenji Kawaguchi, Jiaoyang Huang

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly…

stat.ML2019

Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization

Kenji Kawaguchi, Haihao Lu

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-…

stat.ML2019

Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy

Alex Lamb, Vikas Verma, Kenji Kawaguchi +4

Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as a…

stat.ML2019

Every Local Minimum Value is the Global Minimum Value of Induced Model in Non-convex Machine Learning

Kenji Kawaguchi, Jiaoyang Huang, Leslie Pack Kaelbling

For nonconvex optimization in machine learning, this article proves that every local minimum achieves the globally optimal value of the perturbable gradient basis model at any diff…

stat.ML2019

Interpolation Consistency Training for Semi-Supervised Learning

Vikas Verma, Kenji Kawaguchi, Alex Lamb +4

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT…