ndexter / MLFA
Machine Learning Function Approximation: This code implements the fully-connected Deep Neural Network (DNN) architectures considered in the paper "The gap between theory and practice in function approximation with deep neural networks" available at https://arxiv.org/abs/2001.07523
☆18Updated 4 years ago
Alternatives and similar repositories for MLFA:
Users that are interested in MLFA are comparing it to the libraries listed below
- Package for CGD and ACGD optimizers☆20Updated 2 years ago
- A differentiation API for PyTorch☆30Updated 4 years ago
- ☆28Updated 5 years ago
- Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)☆86Updated 2 years ago
- Monotone operator equilibrium networks☆51Updated 4 years ago
- Matlab code implementing Hamiltonian Annealed Importance Sampling for importance weight, partition function, and log likelihood estimatio…☆26Updated 10 years ago
- A variational method for fast, approximate inference for stochastic differential equations.☆44Updated 6 years ago
- [NeurIPS'19] Deep Equilibrium Models Jax Implementation☆39Updated 4 years ago
- ☆30Updated 2 years ago
- A pytorch version of hamiltonian monte carlo☆14Updated 5 years ago
- repo for paper: Adaptive Checkpoint Adjoint (ACA) method for gradient estimation in neural ODE☆54Updated 4 years ago
- ☆80Updated 3 years ago
- "Parameter origami" -- folding and unfolding collections of parameters for optimization and sensitivity analysis.☆14Updated last year
- Code for NIPS 2015 "Gradient-Free Hamiltonian Monte Carlo via Effecient Kernel Exponential Families"☆25Updated 6 years ago
- Refining continuous-in-depth neural networks☆39Updated 3 years ago
- ☆22Updated 4 years ago
- Material for 'Mathematics of Deep Learning Workshop' (Invited Talk)☆17Updated last year
- Discontinuous Hamiltonian Monte Carlo in JAX☆41Updated 5 years ago
- Riemannian Convex Potential Maps☆67Updated last year
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆18Updated 3 years ago
- Probabilistic Solution of Differential Equations☆13Updated 2 years ago
- Repository for DTU Special Course, focusing on Variational Inference using Normalizing Flows (VINF). Supervised by Michael Riis Andersen☆25Updated 4 years ago
- Computing gradients and Hessians of feed-forward networks with GPU acceleration☆18Updated last year
- Python 3.6 and TensorFlow implementation of the AReS and MaRS algorithms☆11Updated 5 years ago
- Code for the paper Gaussian process behaviour in wide deep networks☆48Updated 6 years ago
- ☆15Updated 4 years ago
- Neural Fixed-Point Acceleration for Convex Optimization☆29Updated 2 years ago
- simple JAX-/NumPy-based implementations of NGD with exact/approximate Fisher Information Matrix both in parameter-space and function-spac…☆14Updated 4 years ago
- Official Implementation of "Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics" …☆26Updated 2 years ago
- Prototypes of differentiable differential equation solvers in JAX.☆27Updated 5 years ago