No article text was recorded for this version.
automatic differentiation overhead
Version 1 of 180 papers86 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations
- Blog: SHoP: A Deep Learning Framework for Solving High-Order Partial Differential Equations
- Blog: Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning
- Blog: Collapsing Taylor Mode Automatic Differentiation
- Blog: Deep finite volume method for partial differential equations
- Blog: Solving Fokker-Planck equation using deep learning
- Blog: High Order Numerical Approximation of the Invariant Measure of Ergodic SDEs
- Blog: TaSIL: Taylor Series Imitation Learning
- Blog: Extending Contextual Self-Modulation: Meta-Learning Across Modalities, Task Dimensionalities, and Data Regimes
- Blog: Learning in Integer Latent Variable Models with Nested Automatic Differentiation
- Blog: Separable Physics-Informed Neural Networks
- Blog: Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
- Blog: Differential Algebra Structures on Familes of Trees
- Blog: Differentiable Fluids with Solid Coupling for Learning and Control
- Blog: Astral: training physics-informed neural networks with error majorants
- Blog: A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks
- Blog: Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation
- Blog: Separable PINN: Mitigating the Curse of Dimensionality in Physics-Informed Neural Networks
- Blog: Learning and Transferring Physical Models through Derivatives
- Blog: Solving Poisson Equations using Neural Walk-on-Spheres
- Blog: Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
- Blog: Trajectory Consistency for One-Step Generation on Euler Mean Flows
- Blog: Scalable Higher-order Nonlinear Solvers via Higher-order Automatic Differentiation
- Blog: A derivative-free method for solving elliptic partial differential equations with deep neural networks
- Blog: Evaluating higher derivative tensors by forward propagation of univariate Taylor series
- Blog: A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks
- Blog: Beyond Derivative Pathology of PINNs: Variable Splitting Strategy with Convergence Analysis
- Blog: HoD-Net: High-Order Differentiable Deep Neural Networks and Applications
- Blog: PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design
- Blog: Neural Spectral Methods: Self-supervised learning in the spectral domain
- Blog: A review of automatic differentiation and its efficient implementation
- Blog: Optimizing Automatic Differentiation with Deep Reinforcement Learning
- Blog: Spectral-Informed Neural Networks Outperform Spectral methods in High-dimensional PDEs
- Blog: A refined mean field approximation of synchronous discrete-time population models
- Blog: Self-Consistent Velocity Matching of Probability Flows
- Blog: How does PDE order affect the convergence of PINNs?
- Blog: PIXEL: Physics-Informed Cell Representations for Fast and Accurate PDE Solvers
- Blog: Learning Only On Boundaries: a Physics-Informed Neural operator for Solving Parametric Partial Differential Equations in Complex Geometries
- Blog: Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems
- Blog: Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
- Blog: 3DMeshNet: A Three-Dimensional Differential Neural Network for Structured Mesh Generation
- Blog: Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
- Blog: SepONet: Efficient Large-Scale Physics-Informed Operator Learning
- Blog: Bias-Variance Trade-off in Physics-Informed Neural Networks with Randomized Smoothing for High-Dimensional PDEs
- Blog: Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
- Blog: DOF: Accelerating High-order Differential Operators with Forward Propagation
- Blog: Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
- Blog: Compile-Time Symbolic Differentiation Using C++ Expression Templates
- Blog: Zero Coordinate Shift: Whetted Automatic Differentiation for Physics-informed Operator Learning
- Blog: High-order Differentiable Autoencoder for Nonlinear Model Reduction
- Blog: k-space Physics-informed Neural Network (k-PINN) for Compressed Spectral Mapping and Efficient Inversion of Vibrations in Thin Composite Laminates
- Blog: Fourier Heuristic Pinns to Solve the Biharmonic Equations Based on its Coupled Scheme
- Blog: HOPE: High-order Polynomial Expansion of Black-box Neural Networks
- Blog: SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference
- Blog: Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning
- Blog: Physics-informed Neural Network Combined with Characteristic-Based Split for Solving Navier-Stokes Equations
- Blog: Separable Operator Networks
- Blog: Exact Inference for Integer Latent-Variable Models
- Blog: GeoWarp: An automatically differentiable and GPU-accelerated implicit MPM framework for geomechanics based on NVIDIA Warp
- Blog: DGNN: A Neural PDE Solver Induced by Discontinuous Galerkin Methods
Showing 60 of 80 papers.
History & citation
Current · Permanent link
- This direction split from Efficient High-Order Derivatives for Physics-Informed Neural Networks (85% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_automatic_differentiation_overhead_7707923c,
title = {automatic differentiation overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/automatic-differentiation-overhead/rdr_7707923ce6854f59a185bbe801518ed7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_automatic_differentiation_overhead_7707923c_v1,
title = {automatic differentiation overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/automatic-differentiation-overhead/rdr_7707923ce6854f59a185bbe801518ed7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}