auto-differentiation/xad-py
High-Performance Automatic Differentiation for Python
This library helps quantitative analysts, machine learning engineers, and scientists efficiently calculate derivatives of complex mathematical functions embedded in computer programs. You input your equations and a set of independent variables, and it provides the exact derivatives of your outputs with respect to those inputs. This is crucial for tasks like training models or optimizing systems where you need to understand how small changes in inputs affect results.
No commits in the last 6 months. Available on PyPI.
Use this if you need to precisely and quickly compute first-order derivatives for mathematical models or algorithms, especially in production environments where performance is critical.
Not ideal if you only need symbolic differentiation for very simple functions or if you are not working with Python in a computational or data science context.
Stars
19
Forks
1
Language
Python
License
AGPL-3.0
Category
Last pushed
Sep 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/auto-differentiation/xad-py"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/