NeurIPS 2019:Generalization Bounds of stochastic Gradient Descent for Wide and Deep Neural Networks

NeurIPS 2019:Generalization Bounds of stochastic Gradient Descent for Wide and Deep Neural Networks

Bao Wang: "Momentum in Stochastic Gradient Descent and Deep Neural Nets"Подробнее

Bao Wang: 'Momentum in Stochastic Gradient Descent and Deep Neural Nets'

[NeurIPS 2020] Federated Accelerated Stochastic Gradient DescentПодробнее

[NeurIPS 2020] Federated Accelerated Stochastic Gradient Descent

Towards Building a Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural NetworksПодробнее

Towards Building a Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks

A short video for Neurips2019 paper, Fast and Accurate Stochastic Gradient Descent.Подробнее

A short video for Neurips2019 paper, Fast and Accurate Stochastic Gradient Descent.

NeurIPS 2019 | On Exact Computation with an Infinitely Wide Neural NetПодробнее

NeurIPS 2019 | On Exact Computation with an Infinitely Wide Neural Net

Pratik Chaudhari: "Unraveling the mysteries of stochastic gradient descent on deep neural networks"Подробнее

Pratik Chaudhari: 'Unraveling the mysteries of stochastic gradient descent on deep neural networks'

Let's Build a NEURAL NETWORK! | MathПодробнее

Let's Build a NEURAL NETWORK! | Math

Lecture 9: Information-Theoretic Generalization Bounds for Stochastic Gradient Descent (English)Подробнее

Lecture 9: Information-Theoretic Generalization Bounds for Stochastic Gradient Descent (English)

Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regim | ICLR 2021Подробнее

Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regim | ICLR 2021

Understanding Gradient Descent for Over-parameterized Deep Neural NetworksПодробнее

Understanding Gradient Descent for Over-parameterized Deep Neural Networks

Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical ViewpointsПодробнее

Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints

Stochastic Gradient Descent: where optimization meets machine learning- Rachel WardПодробнее

Stochastic Gradient Descent: where optimization meets machine learning- Rachel Ward

Uniform convergence may be unable to explain generalization in deep learning | NeurIPSПодробнее

Uniform convergence may be unable to explain generalization in deep learning | NeurIPS

Optimization for Deep Learning (Momentum, RMSprop, AdaGrad, Adam)Подробнее

Optimization for Deep Learning (Momentum, RMSprop, AdaGrad, Adam)

NeurIPS 2019 Test of Time Award - Lin XiaoПодробнее

NeurIPS 2019 Test of Time Award - Lin Xiao

Lecture 4 - Deep Learning Foundations: the implicit bias of gradient descentПодробнее

Lecture 4 - Deep Learning Foundations: the implicit bias of gradient descent

NeurIPS 2019 Outstanding New Directions Paper Award w/ slidesПодробнее

NeurIPS 2019 Outstanding New Directions Paper Award w/ slides