aangelopoulos/ltt
Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control
This is a tool for researchers and developers working with predictive algorithms, especially in computer vision or machine learning. It helps reproduce experiments from the "Learn then Test" paper, focusing on how to calibrate algorithms to control risk. Users input experiment scripts and specific environment setups to validate or extend research findings related to predictive accuracy and risk management.
No commits in the last 6 months.
Use this if you are a researcher or developer needing to reproduce, validate, or build upon experiments for calibrating predictive algorithms to control risk, particularly those detailed in the "Learn then Test" paper.
Not ideal if you are an end-user looking for a pre-built application or a simple, off-the-shelf solution for risk control, as this requires technical expertise to set up and run experiments.
Stars
72
Forks
10
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aangelopoulos/ltt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sktime/skpro
A unified framework for tabular probabilistic regression, time-to-event prediction, and...
WenjieDu/Awesome_Imputation
Awesome Deep Learning for Time-Series Imputation, including an unmissable paper and tool list...
WenjieDu/PyGrinder
PyGrinder: a Python toolkit for grinding data beans into the incomplete for real-world data...
DoubleML/doubleml-for-r
DoubleML - Double Machine Learning in R
ocbe-uio/imml
A Python package for integrating, processing, and analyzing incomplete multi-modal datasets.