Regularization Python Packages

dropblock

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

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.

pyclsp

A modular two-step convex optimization estimator for ill-posed problems

pytmpinv

Tabular Matrix Problems via Pseudoinverse Estimation

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.

early-stopping-pytorch

Early stopping for PyTorch

pylppinv

Linear Programming via Regularized Least Squares

l1tv

Denoising/reconstruction of piecewise constant signals using the L1TV model

tomobar

TOmographic MOdel-BAsed Reconstruction (ToMoBAR) software

pyunfold

Iterative unfolding for Python

mlektic

A Python ML library to use and visualize gradient descent for linear and logistic regression optimization.

l0learn

Efficient Algorithms for L0 Regularized Learning

condat-tv

Python wrapper for the fast TV denoising algorithm by Laurent Condat

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.

ear-transformers

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

torch-layer-normalization

Layer normalization in PyTorch

lppinv

Linear Programming via Regularized Least Squares

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.

stochdepth

Deep Networks with Stochastic Depth for PyTorch

libnmf

Optimization and Regularization variants of NMF