Follow
Johannes Lederer
Johannes Lederer
Professor of Data-Driven Methods, University of Hamburg
Verified email at uni-hamburg.de - Homepage
Title
Cited by
Cited by
Year
On the prediction performance of the lasso
AS Dalalyan, M Hebiri, J Lederer
2002017
How correlations influence lasso prediction
M Hebiri, J Lederer
IEEE Transactions on Information Theory 59 (3), 1846-1854, 2012
1422012
The group square-root lasso: Theoretical properties and fast algorithms
F Bunea, J Lederer, Y She
IEEE Transactions on Information Theory 60 (2), 1313-1325, 2013
1172013
The Bernstein–Orlicz norm and deviation inequalities
S van de Geer, J Lederer
Probability theory and related fields 157 (1), 225-250, 2013
982013
Activation functions in artificial neural networks: A systematic overview
J Lederer
arXiv preprint arXiv:2101.09957, 2021
842021
Don't fall for tuning parameters: Tuning-free variable selection in high dimensions with the TREX
J Lederer, C Müller
Proceedings of the AAAI conference on artificial intelligence 29 (1), 2015
762015
A practical scheme and fast algorithm to tune the lasso with optimality guarantees
M Chichignoud, J Lederer, MJ Wainwright
Journal of Machine Learning Research 17 (229), 1-20, 2016
70*2016
The Lasso, correlated design, and improved oracle inequalities
S Van de Geer, J Lederer
From Probability to Statistics and Back: High-Dimensional Models and …, 2013
682013
Is there a role for statistics in artificial intelligence?
S Friedrich, G Antes, S Behr, H Binder, W Brannath, F Dumpert, K Ickstadt, ...
Advances in Data Analysis and Classification 16 (4), 823-846, 2022
662022
Inference for high-dimensional instrumental variables regression
D Gold, J Lederer, J Tao
Journal of Econometrics 217 (1), 79-111, 2020
492020
Oracle inequalities for high-dimensional prediction
J Lederer, L Yu, I Gaynanova
402019
New concentration inequalities for suprema of empirical processes
J Lederer, S Van De Geer
Bernoulli, 2020-2038, 2014
392014
Fundamentals of High-Dimensional Statistics
J Lederer
Springer International Publishing, Cham, Switzerland, 2022
36*2022
Trust, but verify: benefits and pitfalls of least-squares refitting in high dimensions
J Lederer
arXiv preprint arXiv:1306.0113, 2013
342013
Statistical guarantees for regularized neural networks
M Taheri, F Xie, J Lederer
Neural Networks 142, 148-161, 2021
332021
Risk bounds for robust deep learning
J Lederer
arXiv preprint arXiv:2009.06202, 2020
232020
Non-convex global minimization and false discovery rate control for the TREX
J Bien, I Gaynanova, J Lederer, CL Müller
Journal of Computational and Graphical Statistics 27 (1), 23-33, 2018
232018
Integrating additional knowledge into the estimation of graphical models
Y Bu, J Lederer
The international journal of biostatistics 18 (1), 1-17, 2022
212022
Optimal two-step prediction in regression
D Chételat, J Lederer, J Salmon
212017
Prediction Error Bounds for Linear Regression With the TREX
jacob bien, irina gaynanova, johannes lederer, christian müller
https://arxiv.org/abs/1801.01394, 0
21*
The system can't perform the operation now. Try again later.
Articles 1–20