Johannes Lederer

research

∙ 03/07/2023

Extremes in High Dimensions: Methods and Scalable Algorithms

Extreme-value theory has been explored in considerable detail for univar...

0 Johannes Lederer, et al. ∙

research

∙ 03/03/2023

Lag selection and estimation of stable parameters for multiple autoregressive processes through convex programming

Motivated by a variety of applications, high-dimensional time series hav...

0 Somnath Chakraborty, et al. ∙

research

∙ 02/22/2023

The DeepCAR Method: Forecasting Time-Series Data That Have Change Points

Many methods for time-series forecasting are known in classical statisti...

0 Ayla Jungbluth, et al. ∙

research

∙ 02/16/2023

Reducing Computational and Statistical Complexity in Machine Learning Through Cardinality Sparsity

High-dimensional data has become ubiquitous across the sciences but caus...

0 Ali Mohades, et al. ∙

research

∙ 12/11/2022

Statistical guarantees for sparse deep learning

Neural networks are becoming increasingly popular in applications, but o...

0 Johannes Lederer, et al. ∙

research

∙ 06/21/2022

Marginal Tail-Adaptive Normalizing Flows

Learning the tail behavior of a distribution is a notoriously difficult ...

0 Mike Laszkiewicz, et al. ∙

research

∙ 05/09/2022

Statistical Guarantees for Approximate Stationary Points of Simple Neural Networks

Since statistical guarantees for neural networks are usually restricted ...

0 Mahsa Taheri, et al. ∙

research

∙ 02/02/2022

VC-PCR: A Prediction Method based on Supervised Variable Selection and Clustering

Sparse linear prediction methods suffer from decreased prediction accura...

0 Rebecca Marion, et al. ∙

research

∙ 01/13/2022

Depth Normalization of Small RNA Sequencing: Using Data and Biology to Select a Suitable Method

Deep sequencing has become one of the most popular tools for transcripto...

0 Yannick Düren, et al. ∙

research

∙ 07/15/2021

Copula-Based Normalizing Flows

Normalizing flows, which learn a distribution by transforming the data t...

0 Mike Laszkiewicz, et al. ∙

research

∙ 06/04/2021

Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks

Deep learning requires several design choices, such as the nodes' activa...

0 Leni Ven, et al. ∙

research

∙ 05/28/2021

Targeted Deep Learning: Framework, Methods, and Applications

Deep learning systems are typically designed to perform for a wide range...

0 Shih-Ting Huang, et al. ∙

research

∙ 05/28/2021

DeepMoM: Robust Deep Learning With Median-of-Means

Data used in deep learning is notoriously problematic. For example, data...

0 Shih-Ting Huang, et al. ∙

research

∙ 01/25/2021

Activation Functions in Artificial Neural Networks: A Systematic Overview

Activation functions shape the outputs of artificial neurons and, theref...

1 Johannes Lederer, et al. ∙

research

∙ 10/02/2020

No Spurious Local Minima: on the Optimization Landscapes of Wide and Deep Neural Networks

Empirical studies suggest that wide neural networks are comparably easy ...

0 Johannes Lederer, et al. ∙

research

∙ 09/14/2020

Risk Bounds for Robust Deep Learning

It has been observed that certain loss functions can render deep-learnin...

0 Johannes Lederer, et al. ∙

research

∙ 09/13/2020

Is there a role for statistics in artificial intelligence?

The research on and application of artificial intelligence (AI) has trig...

0 Sarah Friedrich, et al. ∙

research

∙ 06/28/2020

Layer Sparsity in Neural Networks

Sparsity has become popular in machine learning, because it can save com...

0 Mohamed Hebiri, et al. ∙

research

∙ 05/30/2020

Statistical Guarantees for Regularized Neural Networks

Neural networks have become standard tools in the analysis of data, but ...

0 Mahsa Taheri, et al. ∙

research

∙ 05/01/2020

Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery

The graphical lasso is the most popular estimator in Gaussian graphical ...

0 Mike Laszkiewicz, et al. ∙

research

∙ 04/24/2020

Estimating the Lasso's Effective Noise

Much of the theory for the lasso in the linear model Y = X β^* + ε hinge...

0 Johannes Lederer, et al. ∙

research

∙ 02/27/2020

Tuning-free ridge estimators for high-dimensional generalized linear models

Ridge estimators regularize the squared Euclidean lengths of parameters....

0 Shih-Ting Huang, et al. ∙

research

∙ 09/23/2019

Tuning parameter calibration for prediction in personalized medicine

Personalized medicine has become an important part of medicine, for inst...

0 Shih-Ting Huang, et al. ∙

research

∙ 07/08/2019

False Discovery Rates in Biological Networks

The increasing availability of data has generated unprecedented prospect...

0 Lu Yu, et al. ∙

research

∙ 07/08/2019

Aggregated False Discovery Rate Control

We propose an aggregation scheme for methods that control the false disc...

0 Fang Xie, et al. ∙

research

∙ 01/04/2018

Prediction Error Bounds for Linear Regression With the TREX

The TREX is a recently introduced approach to sparse linear regression. ...

0 Jacob Bien, et al. ∙

research

∙ 10/09/2017

Maximum Regularized Likelihood Estimators: A General Prediction Theory and Applications

Maximum regularized likelihood estimators (MRLEs) are arguably the most ...

0 Rui Zhuang, et al. ∙

research

∙ 04/10/2017

Integrating Additional Knowledge Into Estimation of Graphical Models

In applications of graphical models, we typically have more information ...

0 Yunqi Bu, et al. ∙

research

∙ 10/01/2016

Tuning Parameter Calibration in High-dimensional Logistic Regression With Theoretical Guarantees

Feature selection is a standard approach to understanding and modeling h...

0 Wei Li, et al. ∙

research

∙ 09/23/2016

Efficient Feature Selection With Large and High-dimensional Data

Driven by the advances in technology, large and high-dimensional data ha...

0 Néhémy Lim, et al. ∙

research

∙ 08/01/2016

Oracle Inequalities for High-dimensional Prediction

The abundance of high-dimensional data in the modern sciences has genera...

0 Johannes Lederer, et al. ∙

research

∙ 04/22/2016

Non-convex Global Minimization and False Discovery Rate Control for the TREX

The TREX is a recently introduced method for performing sparse high-dime...

0 Jacob Bien, et al. ∙

research

∙ 10/27/2014

Topology Adaptive Graph Estimation in High Dimensions

We introduce Graphical TREX (GTREX), a novel method for graph estimation...

0 Johannes Lederer, et al. ∙

research

∙ 09/16/2014

Compute Less to Get More: Using ORC to Improve Sparse Filtering

Sparse Filtering is a popular feature learning algorithm for image class...

0 Johannes Lederer, et al. ∙

research

∙ 04/02/2014

Don't Fall for Tuning Parameters: Tuning-Free Variable Selection in High Dimensions With the TREX

Lasso is a seminal contribution to high-dimensional statistics, but it h...

0 Johannes Lederer, et al. ∙

research

∙ 02/07/2014

On the Prediction Performance of the Lasso

Although the Lasso has been extensively studied, the relationship betwee...

0 Arnak S. Dalalyan, et al. ∙

Johannes Lederer

Featured Co-authors