5 citations · 7 across the 5 of their papers we have counts for
5 papers · 1 filter
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…
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…
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…
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…
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…