Gradually-Warmup Learning Rate Scheduler for PyTorch
-
Updated
Jul 15, 2021 - Python
Gradually-Warmup Learning Rate Scheduler for PyTorch
Federated Optimization in Heterogeneous Networks (MLSys '20)
Large-scale, multi-GPU capable, kernel solver
Tensorflow source code for "CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise" (CVPR 2018)
Learning M-Way Tree - Web Scale Clustering - EM-tree, K-tree, k-means, TSVQ, repeated k-means, bitwise clustering
Riemannian stochastic optimization algorithms: Version 1.0.3
Scaling Object Detection by Transferring Classification Weights
i-RIM applied to the fastMRI challenge data.
Code for reproducing the experiments on large-scale pre-training and transfer learning for the paper "Effect of large-scale pre-training on full and few-shot transfer learning for natural and medical images" (https://arxiv.org/abs/2106.00116)
MISSION: Ultra Large-Scale Feature Selection using Count-Sketches
LIBS2ML: A Library for Scalable Second Order Machine Learning Algorithms
A curated list of papers on large-scale graph learning.
Fast Factorization Machines
Network of Experts for Large-Scale Image Categorization [ECCV 2016]
Enitor provides the MATLAB implementation of several large-scale kernel methods.
Machine Learning Platform Based on PS-Lite
A distributed implementation of "Nested Subtree Hash Kernels for Large-Scale Graph Classification Over Streams" (ICDM 2012).
Universal ML: Large Scale Distributed Machine Learning (Deep Learning) Systems
Falkon is one of the most efficient algorithm able to work in a supervised large scale setting. This method is the result of a combination of three simple principles: sub-sampling, preconditioning and iterative solvers. In order to extend FALKON usability we have designed an extension able to work in a semi-supervised scenario.
Add a description, image, and links to the large-scale-learning topic page so that developers can more easily learn about it.
To associate your repository with the large-scale-learning topic, visit your repo's landing page and select "manage topics."