activity
20162022
most citedBeating SGD Saturation with Tail-Averaging and Minibatching

5 citations · 7 across the 5 of their papers we have counts for

collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2022

Local SGD in Overparameterized Linear Regression

Mike Nguyen, Charly Kirst, Nicole Mücke

We consider distributed learning using constant stepsize SGD (DSGD) over several devices, each sending a final model update to a central server. In a final step, the local estimate…

stat.ML2021

Data splitting improves statistical performance in overparametrized regimes

Nicole Mücke, Enrico Reiss, Jonas Rungenhagen +1

While large training datasets generally offer improvement in model performance, the training process becomes computationally expensive and time consuming. Distributed learning is a…

stat.ML20202 cited

Stochastic Gradient Descent in Hilbert Scales: Smoothness, Preconditioning and Earlier Stopping

Nicole Mücke, Enrico Reiss

Stochastic Gradient Descent (SGD) has become the method of choice for solving a broad range of machine learning problems. However, some of its learning properties are still not ful…

stat.ML20195 cited

Beating SGD Saturation with Tail-Averaging and Minibatching

Nicole Mücke, Gergely Neu, Lorenzo Rosasco

While stochastic gradient descent (SGD) is one of the major workhorses in machine learning, the learning properties of many practically used variants are poorly understood. In this…

stat.ML2016

Optimal Rates For Regularization Of Statistical Inverse Learning Problems

Gilles Blanchard, Nicole Mücke

We consider a statistical inverse learning problem, where we observe the image of a function through a linear operator at i.i.d. random design points , superposed with…