conftrace_

2020 JMLR JMLR 2020

metric-learn: Metric Learning Algorithms in Python

Abstract

metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms. As part of scikit-learn-contrib, it provides a unified interface compatible with scikit-learn which allows to easily perform cross-validation, model selection, and pipelining with other machine learning estimators. metric-learn is thoroughly tested and available on PyPi under the MIT license. [abs] [ pdf ][ bib ] [ code ] © JMLR 2020. (edit, beta)

Authors

William de Vazelhes, CJ Carey, Yuan Tang, Nathalie Vauquier, Aurélien Bellet

Topics

Machine Learning > Core Methods > Metric Learning Machine Learning > Core Methods > Embedding Learning Machine Learning > Learning Types > Weakly Supervised Learning

Keywords

metric learning weakly supervised learning distance metric learning distance metric

More from JMLR 2020

All JMLR 2020 papers →

A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks

Convergence Rates for the Stochastic Gradient Descent Method for Non-Convex Objective Functions

Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting

Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Importance Sampling Techniques for Policy Optimization