1.6k citations · 2.7k across the 28 of their papers we have counts for
5 papers · 1 filter
Reconciling modern machine learning practice and the bias-variance trade-off
Mikhail Belkin, Daniel Hsu, Siyuan Ma +1
Breakthroughs in machine learning are rapidly changing science and society, yet our fundamental understanding of this technology has lagged far behind. Indeed, one of the central t…
On exponential convergence of SGD in non-convex over-parametrized learning
Raef Bassily, Mikhail Belkin, Siyuan Ma
Large over-parametrized models learned via stochastic gradient descent (SGD) methods have become a key element in modern machine learning. Although SGD methods are very effective i…
Kernel Machines Beat Deep Neural Networks on Mask-based Single-channel Speech Enhancement
Like Hui, Siyuan Ma, Mikhail Belkin
We apply a fast kernel method for mask-based single-channel speech enhancement. Specifically, our method solves a kernel regression problem associated to a non-smooth kernel functi…
Kernel machines that adapt to GPUs for effective large batch training
Siyuan Ma, Mikhail Belkin
Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a…
To understand deep learning we need to understand kernel learning
Mikhail Belkin, Siyuan Ma, Soumik Mandal
Generalization performance of classifiers in deep learning has recently become a subject of intense study. Deep models, typically over-parametrized, tend to fit the training data e…