166 citations · 424 across the 44 of their papers we have counts for
11 papers · 1 filter
The DeepCAR Method: Forecasting Time-Series Data That Have Change Points
Ayla Jungbluth, Johannes Lederer
Many methods for time-series forecasting are known in classical statistics, such as autoregression, moving averages, and exponential smoothing. The DeepAR framework is a novel, rec…
Statistical guarantees for sparse deep learning
Johannes Lederer
Neural networks are becoming increasingly popular in applications, but our mathematical understanding of their potential and limitations is still limited. In this paper, we further…
Marginal Tail-Adaptive Normalizing Flows
Mike Laszkiewicz, Johannes Lederer, Asja Fischer
Learning the tail behavior of a distribution is a notoriously difficult problem. By definition, the number of samples from the tail is small, and deep generative models, such as no…
Copula-Based Normalizing Flows
Mike Laszkiewicz, Johannes Lederer, Asja Fischer
Normalizing flows, which learn a distribution by transforming the data to samples from a Gaussian base distribution, have proven powerful density approximations. But their expressi…
Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks
Leni Ven, Johannes Lederer
Deep learning requires several design choices, such as the nodes' activation functions and the widths, types, and arrangements of the layers. One consideration when making these ch…
Targeted Deep Learning: Framework, Methods, and Applications
Shih-Ting Huang, Johannes Lederer
Deep learning systems are typically designed to perform for a wide range of test inputs. For example, deep learning systems in autonomous cars are supposed to deal with traffic sit…
Activation Functions in Artificial Neural Networks: A Systematic Overview
Johannes Lederer
Activation functions shape the outputs of artificial neurons and, therefore, are integral parts of neural networks in general and deep learning in particular. Some activation funct…
Optimization Landscapes of Wide Deep Neural Networks Are Benign
Johannes Lederer
We analyze the optimization landscapes of deep learning with wide networks. We highlight the importance of constraints for such networks and show that constraint -- as well as unco…
Risk Bounds for Robust Deep Learning
Johannes Lederer
It has been observed that certain loss functions can render deep-learning pipelines robust against flaws in the data. In this paper, we support these empirical findings with statis…
Layer Sparsity in Neural Networks
Mohamed Hebiri, Johannes Lederer
Sparsity has become popular in machine learning, because it can save computational resources, facilitate interpretations, and prevent overfitting. In this paper, we discuss sparsit…
Statistical Guarantees for Regularized Neural Networks
Mahsa Taheri, Fang Xie, Johannes Lederer
Neural networks have become standard tools in the analysis of data, but they lack comprehensive mathematical theories. For example, there are very few statistical guarantees for le…