Popular GitHub Repositories for Sgd

LSTM and QRNN Language Model Toolkit for PyTorch

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

Ternary Gradients to Reduce Communication in Distributed Deep Learning (TensorFlow)

A Deep Learning and preprocessing framework in Rust with support for CPU and GPU.

Distributed Learning by Pair-Wise Averaging

A C++ toolkit for Convex Optimization (Logistic Loss, SVM, SVR, Least Squares etc.), Convex Optimization algorithms (LBFGS, TRON, SGD, AdsGrad, CG, Nesterov etc.) and Classifiers/Regressors (Logistic Regression, SVMs, Least Squares Regression etc.)

Implementation of key concepts of neuralnetwork via numpy

Amortized version of the differentially private SGD algorithm published in "Deep Learning with Differential Privacy" by Abadi et al. Enforces privacy by clipping and sanitising the gradients with Gaussian noise during training.

Notes & Code to go over "Grokking Deep Learning" Book by Andrew Trask

vector quantization for stochastic gradient descent.

Distributed Momentum for Byzantine-resilient Stochastic Gradient Descent (ICLR 2021)

Distributed Fieldaware Factorization Machines based on Parameter Server

Implementation of the algorithms described in the papers "ZO-AdaMM: Zeroth Order Adaptive Momentum" by Chen et al., "Stochastic first- and zeroth-order methods" by Ghadimi et al. and "SignSGD via zeroth- order oracle" by Liu et al.

My beautiful Neural Network made from scratch and love. It plays the game Flappy-Birds flawlessly, in 3 to 9 generations!!

This repository provides a unified framework to perform Optimization experiments across Stochastic, Mini-Batch, Decentralized and Federated Setting.

Implementa un sistema para clasificar imágenes en diferentes categorías utilizando técnicas avanzadas de aprendizaje profundo. Combina clasificadores lineales, redes neuronales convolucionales y modelos preentrenados como EfficientNet, con procesamiento y visualización realizados mediante PyTorch.

Analyze the performance of 7 optimizers by varying their learning rates

Implements the NNDL book's "network.py" code (Chapter 1) to improve its functionality and performance.