Search Results for author:
Found 38 papers, 11 papers with code
Benchmarking the Fairness of Image Upsampling Methods
Recent years have witnessed a rapid development of deep generative models for creating synthetic media, such as images and videos.
Affine Invariance in Continuous-Domain Convolutional Neural Networks
The notion of group invariance helps neural networks in recognizing patterns and features under geometric transformations.
Set-Membership Inference Attacks using Data Watermarking
In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques.
Single-Model Attribution of Generative Models Through Final-Layer Inversion
Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution.
Lag selection and estimation of stable parameters for multiple autoregressive processes through convex programming
We prove that the estimated process is stable, and we establish rates for the forecasting error that can outmatch the known rate in our setting.
The DeepCAR Method: Forecasting Time-Series Data That Have Change Points
Many methods for time-series forecasting are known in classical statistics, such as autoregression, moving averages, and exponential smoothing.
Statistical guarantees for sparse deep learning
Neural networks are becoming increasingly popular in applications, but our mathematical understanding of their potential and limitations is still limited.
Marginal Tail-Adaptive Normalizing Flows
Learning the tail behavior of a distribution is a notoriously difficult problem.
Statistical Guarantees for Approximate Stationary Points of Simple Neural Networks
Since statistical guarantees for neural networks are usually restricted to global optima of intricate objective functions, it is not clear whether these theories really explain the performances of actual outputs of neural-network pipelines.
VC-PCR: A Prediction Method based on Supervised Variable Selection and Clustering
Sparse linear prediction methods suffer from decreased prediction accuracy when the predictor variables have cluster structure (e. g. there are highly correlated groups of variables).
Depth Normalization of Small RNA Sequencing: Using Data and Biology to Select a Suitable Method
To address this problem, we developed "DANA" - an approach for assessing the performance of normalization methods for microRNA sequencing data based on biology-motivated and data-driven metrics.
Copula-Based Normalizing Flows
Normalizing flows, which learn a distribution by transforming the data to samples from a Gaussian base distribution, have proven powerful density approximations.
Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks
Deep learning requires several design choices, such as the nodes' activation functions and the widths, types, and arrangements of the layers.
Targeted Deep Learning: Framework, Methods, and Applications
In this paper, we introduce a framework for targeted deep learning, and we devise and test an approach for adapting standard pipelines to the requirements of targeted deep learning.
DeepMoM: Robust Deep Learning With Median-of-Means
In contrast, the arguably much more common case of corruption that reflects the limited quality of data has been studied much less.
Activation Functions in Artificial Neural Networks: A Systematic Overview
Activation functions shape the outputs of artificial neurons and, therefore, are integral parts of neural networks in general and deep learning in particular.
Connection- and Node-Sparse Deep Learning: Statistical Guarantees
Neural networks are becoming increasingly popular in applications, but a comprehensive mathematical understanding of their potentials and limitations is still missing.
Optimization Landscapes of Wide Deep Neural Networks Are Benign
We analyze the optimization landscapes of deep learning with wide networks.
No Spurious Local Minima: on the Optimization Landscapes of Wide and Deep Neural Networks
Empirical studies suggest that wide neural networks are comparably easy to optimize, but mathematical support for this observation is scarce.
Risk Bounds for Robust Deep Learning
It has been observed that certain loss functions can render deep-learning pipelines robust against flaws in the data.
Is there a role for statistics in artificial intelligence?
The research on and application of artificial intelligence (AI) has triggered a comprehensive scientific, economic, social and political discussion.
Layer Sparsity in Neural Networks
Sparsity has become popular in machine learning, because it can save computational resources, facilitate interpretations, and prevent overfitting.
Statistical Guarantees for Regularized Neural Networks
Neural networks have become standard tools in the analysis of data, but they lack comprehensive mathematical theories.
Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery
Many Machine Learning algorithms are formulated as regularized optimization problems, but their performance hinges on a regularization parameter that needs to be calibrated to each application at hand.
Tuning-free ridge estimators for high-dimensional generalized linear models
Ridge estimators regularize the squared Euclidean lengths of parameters.
Tuning parameter calibration for prediction in personalized medicine
Personalized medicine has become an important part of medicine, for instance predicting individual drug responses based on genomic information.
Aggregating Knockoffs for False Discovery Rate Control with an Application to Gut Microbiome Data
We support our method both in theory and simulations, and we show that it can lead to new discoveries on microbiome data from the American Gut Project.
Methodology Quantitative Methods Applications
False Discovery Rates in Biological Networks
The increasing availability of data has generated unprecedented prospects for network analyses in many biological fields, such as neuroscience (e. g., brain networks), genomics (e. g., gene-gene interaction networks), and ecology (e. g., species interaction networks).
Methodology Quantitative Methods Applications
Maximum Regularized Likelihood Estimators: A General Prediction Theory and Applications
Maximum regularized likelihood estimators (MRLEs) are arguably the most established class of estimators in high-dimensional statistics.
Integrating Additional Knowledge Into Estimation of Graphical Models
In applications of graphical models, we typically have more information than just the samples themselves.
Tuning parameter calibration for $\ell_1$-regularized logistic regression
Feature selection is a standard approach to understanding and modeling high-dimensional classification data, but the corresponding statistical methods hinge on tuning parameters that are difficult to calibrate.
Balancing Statistical and Computational Precision: A General Theory and Applications to Sparse Regression
Modern technologies are generating ever-increasing amounts of data.
Oracle Inequalities for High-dimensional Prediction
The abundance of high-dimensional data in the modern sciences has generated tremendous interest in penalized estimators such as the lasso, scaled lasso, square-root lasso, elastic net, and many others.
Non-convex Global Minimization and False Discovery Rate Control for the TREX
The TREX is a recently introduced method for performing sparse high-dimensional regression.
Topology Adaptive Graph Estimation in High Dimensions
We introduce Graphical TREX (GTREX), a novel method for graph estimation in high-dimensional Gaussian graphical models.
Compute Less to Get More: Using ORC to Improve Sparse Filtering
Sparse Filtering is a popular feature learning algorithm for image classification pipelines.
Don't Fall for Tuning Parameters: Tuning-Free Variable Selection in High Dimensions With the TREX
However, Square-Root Lasso still requires the calibration of a tuning parameter to all other aspects of the model.
On the Prediction Performance of the Lasso
Although the Lasso has been extensively studied, the relationship between its prediction performance and the correlations of the covariates is not fully understood.
