Gradient

Official implementation of Conflict-free Inverse Gradients method

A library which Predicts the Y value(output) for given test data points using gradient descent algorithm.

WAsserstein Global Gradient-free OptimisatioN (WAGGON) methods library.

Python package + CLI to generate stylistic wordclouds, including gradients and icon shapes!

Proximal Gradient Methods for Pytorch

Field and gradient calculations for magnetic coils

Gradient-based boundary (GBB) surface refinement

Gradient-Aware Fast MaxVol Technique for Dynamic Data Sampling

GATO: Gradient-based categorization optimization for HEP analyses

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

PyTorch optimizer based on nonlinear conjugate gradient method

Polynomial approximations

**thoad** (Torch High Order Automatic Differentiation) is a lightweight reverse-mode autodifferentiation engine written entirely in Python that works over PyTorch’s computational graph to compute **high order partial derivatives**. Unlike PyTorch’s native autograd - which is limited to first-order native partial derivatives - **thoad** is able to performantly propagate arbitray-order derivatives throughout the graph, enabling more advanced gradient-based computations.

Medical Deep Learning Framework

Medical Deep Learning Framework

Gradient Boosting and Probabilistic Regression with categorical structure

Gradient Boosted Trees for RL

NFNets, PyTorch

A library to build Gradient boosted trees for ordinal labels

Python Sensitivity Analysis - Gradient DataFrames and Hex-Bin Plots

Automatic-Class-Balanced MSE Loss for PyTorch (ACB-MSE) to combat class imbalanced datasets and stabilise fluctuating loss gradients.

A pytorch library that implements differentiable and learnable robot models, which allows users to learn parameters of analytical robot models, and/or propagate gradients through analytical robot computations such as forward kinematics.

Medical Deep Learning Framework.

PulPy: Pulses in Python. A package for MRI RF and gradient pulse design.

Gradient boosting libraries integrated with pytorch

Advanced numerical function interpolation and differentiation with universal API, multivariate calculus, and stochastic extensions

Stochastic Gradient Monte Carlo in Jax

HCP version of Gradient Unwarping Package for Python/Numpy

Method PROTES (PRobabilistic Optimizer with TEnsor Sampling) for derivative-free optimization of the multidimensional arrays and discretized multivariate functions based on the tensor train (TT) format

RotoGrad: Gradient Homogenization in Multitask Learning in Pytorch

A package for applying differential privacy to model training using gradient shuffling and membership inference attack detection.

A high-performance gradient boosting implementation using Cython

A python package containing implementations of two widely used algorithms to minimise any function - Gradient Descent algorithm and the Normal Equation method.

Smart gradient clippers

Fast (and cheeky) differentially private gradient-based optimisation in PyTorch

Gradient boosted decision tree palindrome predictor, used to locate regions for further investigation thru http://palindromes.ibp.cz/

A toolbox for using Constraint Guided Gradient Descent when training neural networks.

Gradient Boosting powered by GPU(NVIDIA CUDA)

Directed evolution of proteins with fast gradient-based discrete MCMC.

Computing and connecting horizontal gradient maxima in potential-field geophysics

A Python package for determining the structures of materials with gradient-based methods.

KFAC-like Structured Inverse-Free Natural Gradient Descent

A comprehensive template system for creating professional business presentations with modern styling, cards, and badges

Unified interface for Gradient Boosted Decision Trees

A python package for the Cyclic Gradient Boosting Machine algorithm

Echo State Gradient Propogation implementation for PyTorch

Deep Neural Network inspection: view weights, gradients and activations

Implementation of Cumulative Spectral Gradient (CSG), a measure to estimate the complexity of datasets. This works has been presented at CVPR 2019.

Gradient Based Class Activation Maps for TensorFlow models.