sophiaas / spectral-universality
Official PyTorch and JAX Implementation of "Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks"
☆38Updated last year
Alternatives and similar repositories for spectral-universality:
Users that are interested in spectral-universality are comparing it to the libraries listed below
- ☆34Updated 3 years ago
- Code repository of the paper "Clifford-Steerable Convolutional Neural Networks"☆47Updated 8 months ago
- Neural Optimal Transport with Lagrangian Costs☆55Updated 9 months ago
- Official repository of Implicit Neural Convolutional Kernels for Steerable CNNs, Zhdanov et al.☆28Updated 2 months ago
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆44Updated 3 months ago
- The Energy Transformer block, in JAX☆57Updated last year
- Deep Networks Grok All the Time and Here is Why☆34Updated 11 months ago
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- ☆13Updated last year
- Supplementary code for the paper "Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces"☆42Updated last year
- Code for "Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations"☆23Updated 2 years ago
- Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (…☆22Updated 2 years ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆70Updated last year
- This repository implements and evaluates convolutional networks on the Möbius strip as toy model instantiations of Coordinate Independent…☆72Updated last year
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆40Updated last year
- Flow-matching algorithms in JAX☆89Updated 8 months ago
- ☆24Updated last year
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆18Updated 3 years ago
- The code for "Diffusion Geometry" (2024).☆42Updated 10 months ago
- JAX exponential map normalising flows on sphere☆17Updated 4 years ago
- Variational Autoencoder with non-euclidean (hyperbolic) latent space☆11Updated 2 years ago
- an Open Collaborative project to explore the implications — theoretical or practical — of the PDE perspective of ConvNets☆22Updated last year
- Official repository of "Spontaneous symmetry breaking in generative diffusion models"☆43Updated 11 months ago
- Wraps PyTorch code in a JIT-compatible way for JAX. Supports automatically defining gradients for reverse-mode AutoDiff.☆51Updated 2 weeks ago
- Implementation of Action Matching for the Schrödinger equation☆24Updated last year
- Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations☆28Updated 2 years ago
- LieTransformer: Equivariant Self-Attention for Lie Groups☆70Updated 9 months ago
- Expressive Sign Equivariant Networks for Spectral Geometric Learning☆16Updated last year
- A library implementing the kernels for and experiments using extrinsic gauge equivariant vector field Gaussian Processes☆25Updated 3 years ago
- Implementation of approximate free-energy minimization in PyTorch☆19Updated 3 years ago