Coordinate-Free Automatic Differentiation
cs.LG, cs.MS, math.DG
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/oogle/jax
Sources
- A Geometric Theory of Higher-Order Automatic Differentiation
- Discrete Exterior Calculus
- Geoopt: Riemannian Optimization in PyTorch
- DeepCurrents: Learning Implicit Representations of Shapes with Boundaries
- Optimistix: modular optimisation in JAX and Equinox
- Neural Conservation Laws: A Divergence-Free Perspective
- The Willing Kingdon Clifford Algebra Library
- Jet Functors and Weil Algebras in Automatic Differentiation: A Geometric Analysis
- A micro Lie theory for state estimation in robotics
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks