RuntianZ/doro
Distributional and Outlier Robust Optimization (ICML 2021)
This project offers an improved way to train machine learning models, especially when your dataset contains unusual or 'outlier' data points. It takes your existing dataset and model architecture, and outputs a more robust model that performs better even when dealing with real-world data imperfections. This is for machine learning practitioners and researchers who build and deploy models for critical applications.
No commits in the last 6 months.
Use this if you are building machine learning models and suspect that outliers in your training data are negatively impacting your model's real-world performance, especially in cases of subpopulation shifts.
Not ideal if your dataset is perfectly clean with no expected outliers, or if you are looking for a general-purpose model training framework rather than an outlier-robust specific solution.
Stars
28
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jul 10, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RuntianZ/doro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
namkoong-lab/dro
A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch
neu-autonomy/nfl_veripy
Formal Verification of Neural Feedback Loops (NFLs)
THUDM/grb
Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for...
MinghuiChen43/awesome-trustworthy-deep-learning
A curated list of trustworthy deep learning papers. Daily updating...
ADA-research/VERONA
A lightweight Python package for setting up robustness experiments and to compute robustness...