Regularization Python Packages

dropblock

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

l1tv

Denoising/reconstruction of piecewise constant signals using the L1TV model

neural-structured-learning

Training neural models with structured signals.

networks

Library which can be used to build feed forward NN, Convolutional Nets, Linear Regression, and Logistic Regression Models.

pytmpinv

Tabular Matrix Problems via Pseudoinverse Estimation

early-stopping-pytorch

Early stopping for PyTorch

mumfordshah2d

Algorithms for edge preserving smoothing based on the Mumford-Shah model

pylppinv

Linear Programming via Regularized Least Squares

pyclsp

Modular Two-Step Convex Optimization Estimator for Ill-Posed Problems

scproject

Transfer Learning of Gene Expression Signatures in Python.

egora

EgoRA — Entropy-Governed Orthogonality Regularization for Adaptation. Dynamic information-theoretic regularization for fine-tuning neural networks.

pyunfold

Iterative unfolding for Python

ear-transformers

Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"

tomobar

TOmographic MOdel-BAsed Reconstruction (ToMoBAR) software

l0learn

Efficient Algorithms for L0 Regularized Learning

mlektic

A simple machine learning python library.

torch-layer-normalization

Layer normalization in PyTorch

egora-diagnostics

EgoRA — Entropy-Governed Orthogonality Regularization for Adaptation. Dynamic information-theoretic regularization for fine-tuning neural networks.

egora-rrl

EgoRA — Entropy-Governed Orthogonality Regularization for Adaptation. Dynamic information-theoretic regularization for fine-tuning neural networks.

condat-tv

Python wrapper for the fast TV denoising algorithm by Laurent Condat

sparklen

A statistical learning toolkit for high-dimensional Hawkes processes in Python

deepc-hunt

[L4DC 2025] Automatic hyperparameter tuning for DeePC. Built by Michael Cummins at the Automatic Control Laboratory, ETH Zurich.

keras-targeted-dropout

Targeted dropout implemented in Keras

lppinv

Linear Programming via Regularized Least Squares