Stars
Particle Gibbs-based optimal control with performance guarantees for unknown systems with latent states
markdown editor with live preview
Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances
A massively parallel, high-level programming language
BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.
[NeurIPS 2021] Galerkin Transformer: a linear attention without softmax for Partial Differential Equations
Machine learning algorithms for many-body quantum systems
Geometric kernels on manifolds, meshes and graphs
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
Koopman Kernels for Learning Dynamical Systems from Trajectory Data
Structured state space sequence models
Positive-definite "approximations" to matrices
Deep universal probabilistic programming with Python and PyTorch
Data Science, Time Complexity and Inferential Uncertainty (TCIU)
[NeurIPS'23 Spotlight] Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance (LPS), in PyTorch
[ICLR'23 Oral] Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
Learning in infinite dimension with neural operators.
A Library for Advanced Deep Time Series Models.
Code for "Deep Signature Transforms" (NeurIPS 2019)
A Python package to learn the Koopman operator.
A convenient way to convert files from DjVu to PDF format while preserving the text layer