research
∙
05/02/2023
Convergence and error analysis of PINNs
Physics-informed neural networks (PINNs) are a promising approach that c...
share
research
∙
01/31/2023
Naive imputation implicitly regularizes high-dimensional linear models
Two different approaches exist to handle missing values for prediction: ...
research
∙
09/30/2022
Sparse tree-based initialization for neural networks
Dedicated neural network (NN) architectures have been designed to handle...
research
∙
02/08/2022
Is interpolation benign for random forests?
Statistical wisdom suggests that very complex models, interpolating trai...
research
∙
02/03/2022
Minimax rate of consistency for linear models with missing values
Missing values arise in most real-world data sets due to the aggregation...
research
∙
12/20/2021
Model-based Clustering with Missing Not At Random Data
In recent decades, technological advances have made it possible to colle...
research
∙
11/19/2020
On the asymptotic rate of convergence of Stochastic Newton algorithms and their Weighted Averaged versions
The majority of machine learning methods can be regarded as the minimiza...
research
∙
10/29/2020
Analyzing the tree-layer structure of Deep Forests
Random forests on the one hand, and neural networks on the other hand, h...
research
∙
05/12/2020
Robust Lasso-Zero for sparse corruption and model selection with missing covariates
We propose Robust Lasso-Zero, an extension of the Lasso-Zero methodology...
research
∙
04/15/2020
Sampling Rates for ℓ^1-Synthesis
This work investigates the problem of signal recovery from undersampled ...
research
∙
02/21/2020
Debiasing Stochastic Gradient Descent to handle missing values
A major caveat of large scale data is their incom-pleteness. We propose ...
research
∙
02/10/2020
Missing Data Imputation using Optimal Transport
Missing data is a crucial issue when applying machine learning algorithm...
research
∙
06/06/2019
Estimation and imputation in Probabilistic Principal Component Analysis with Missing Not At Random data
Missing Not At Random values are considered to be non-ignorable and requ...
research
∙
06/06/2019
Estimation with informative missing data in the low-rank model with random effects
Matrix completion based on low-rank models is very popular and comes wit...
research
∙
12/29/2018
Imputation and low-rank estimation with Missing Non At Random data
Missing values challenge data analysis because many supervised and unsu-...
research
∙
12/11/2018
Convex Regularization and Representer Theorems
We establish a result which states that regularizing an inverse problem ...
research
∙
08/29/2018
Accelerated proximal boosting
Gradient boosting is a prediction method that iteratively combines weak ...
research
∙
06/26/2018
On Representer Theorems and Convex Regularization
We establish a general principle which states that regularizing an inver...
research
∙
06/11/2018
