This paper introduces a smooth method for (structured) sparsity in $\ell_q$ and $\ell_{p,q}$ regularized optimization problems. Optimization of these non-smooth and possibly non-convex problems typically relies on specialized procedures. In contrast, our general framework is compatible with prevalent first-order optimization methods like Stochastic Gradient Descent and accelerated variants without any required modifications. This is accomplished through a smooth optimization transfer, comprising an overparametrization of selected model parameters using Hadamard products and a change of penalties. In the overparametrized problem, smooth and convex $\ell_2$ regularization of the surrogate parameters induces non-smooth and non-convex $\ell_q$ or $\ell_{p,q}$ regularization in the original parametrization. We show that our approach yields not only matching global minima but also equivalent local minima. This is particularly useful in non-convex sparse regularization, where finding global minima is NP-hard and local minima are known to generalize well. We provide a comprehensive overview consolidating various literature strands on sparsity-inducing parametrizations and propose meaningful extensions to existing approaches. The feasibility of our approach is evaluated through numerical experiments, which demonstrate that its performance is on par with or surpasses commonly used implementations of convex and non-convex regularization methods.
This paper describes the implementation of semi-structured deep distributional regression, a flexible framework to learn distributions based on a combination of additive regression models and deep neural networks. deepregression is implemented in both R and Python, using the deep learning libraries TensorFlow and PyTorch, respectively. The implementation consists of (1) a modular neural network building system for the combination of various statistical and deep learning approaches, (2) an orthogonalization cell to allow for an interpretable combination of different subnetworks as well as (3) pre-processing steps necessary to initialize such models. The software package allows to define models in a user-friendly manner using distribution definitions via a formula environment that is inspired by classical statistical model frameworks such as mgcv. The packages' modular design and functionality provides a unique resource for rapid and reproducible prototyping of complex statistical and deep learning models while simultaneously retaining the indispensable interpretability of classical statistical models.
We propose a unifying network architecture for deep distributional learning in which entire distributions can be learned in a general framework of interpretable regression models and deep neural networks. Previous approaches that try to combine advanced statistical models and deep neural networks embed the neural network part as a predictor in an additive regression model. In contrast, our approach estimates the statistical model part within a unifying neural network by projecting the deep learning model part into the orthogonal complement of the regression model predictor. This facilitates both estimation and interpretability in high-dimensional settings. We identify appropriate default penalties that can also be treated as prior distribution assumptions in the Bayesian version of our network architecture. We consider several use-cases in experiments with synthetic data and real world applications to demonstrate the full efficacy of our approach.