72 citations · 210 across the 22 of their papers we have counts for
23 papers
The mixing time of Mean-Field Gibbs-Ornstein-Uhlenbeck processes
Johan Jonasson
We introduce mean-field Gibbs--Ornstein--Uhlenbeck (MFGOU) processes, a class of discrete-time Markov processes with increments of order , whose conditional means approximate…
Noise Sensitivity and Stability of Deep Neural Networks for Binary Classification
Johan Jonasson, Jeffrey E. Steif, Olof Zetterqvist
A first step is taken towards understanding often observed non-robustness phenomena of deep neural net (DNN) classifiers. This is done from the perspective of Boolean functions by…
Optimal subsampling designs
Henrik Imberg, Marina Axelson-Fisk, Johan Jonasson
Subsampling is commonly used to overcome computational and economical bottlenecks in the analysis of finite populations and massive datasets. Existing methods are often limited in…
Elastic Gradient Descent, an Iterative Optimization Method Approximating the Solution Paths of the Elastic Net
Oskar Allerbo, Johan Jonasson, Rebecka Jörnsten
The elastic net combines lasso and ridge regression to fuse the sparsity property of lasso with the grouping property of ridge regression. The connections between ridge regression…
Robust Neural Network Classification via Double Regularization
Olof Zetterqvist, Rebecka Jörnsten, Johan Jonasson
The presence of mislabeled observations in data is a notoriously challenging problem in statistics and machine learning, associated with poor generalization properties for both tra…
Rapid mixing in unimodal landscapes and efficient simulatedannealing for multimodal distributions
Johan Jonasson, Måns Magnusson
We consider nearest neighbor weighted random walks on the -dimensional box that are governed by some function $g:[0,1] \ra [0,\iy)$, by which we mean that standing at $x…