Activation functions in artificial neural networks: A systematic overview
J Lederer - arXiv preprint arXiv:2101.09957, 2021 - arxiv.org
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 functions …
of neural networks in general and deep learning in particular. Some activation functions …
Why do artificially generated data help adversarial robustness
In the adversarial training framework of\cite {carmon2019unlabeled, gowal2021improving},
people use generated/real unlabeled data with pseudolabels to improve adversarial …
people use generated/real unlabeled data with pseudolabels to improve adversarial …
Phase transition from clean training to adversarial training
Adversarial training is one important algorithm to achieve robust machine learning models.
However, numerous empirical results show a great performance degradation from clean …
However, numerous empirical results show a great performance degradation from clean …
Guaranteed approximation error estimation of neural networks and model modification
Approximation error is a key measure in the process of model validation and verification for
neural networks. In this paper, the problems of guaranteed error estimation of neural …
neural networks. In this paper, the problems of guaranteed error estimation of neural …
Statistical guarantees for sparse deep learning
J Lederer - AStA Advances in Statistical Analysis, 2024 - Springer
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 this …
understanding of their potential and limitations is still limited. In this paper, we further this …
Risk bounds for robust deep learning
J Lederer - arXiv preprint arXiv:2009.06202, 2020 - arxiv.org
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 statistical …
against flaws in the data. In this paper, we support these empirical findings with statistical …
Non-asymptotic guarantees for robust statistical learning under infinite variance assumption
There has been a surge of interest in developing robust estimators for models with heavy-
tailed and bounded variance data in statistics and machine learning, while few works …
tailed and bounded variance data in statistics and machine learning, while few works …
[HTML][HTML] Layer sparsity in neural networks
Sparsity has become popular in machine learning because it can save computational
resources, facilitate interpretations, and prevent overfitting. This paper discusses sparsity in …
resources, facilitate interpretations, and prevent overfitting. This paper discusses sparsity in …
How many samples are needed to train a deep neural network?
Neural networks have become standard tools in many areas, yet many important statistical
questions remain open. This paper studies the question of how much data are needed to …
questions remain open. This paper studies the question of how much data are needed to …
PAC-Bayes training for neural networks: sparsity and uncertainty quantification
MF Steffen, M Trabs - arXiv preprint arXiv:2204.12392, 2022 - arxiv.org
We study the Gibbs posterior distribution from PAC-Bayes theory for sparse deep neural
nets in a nonparametric regression setting. To access the posterior distribution, an efficient …
nets in a nonparametric regression setting. To access the posterior distribution, an efficient …