5 papers
Stable and Near-Reversible Diffusion ODE Solvers for Image Editing
Barbora Barancikova, Daniil Shmelev, Cristopher Salvi
The inversion of diffusion models plays a central role in image editing. Algebraically reversible ODE solvers provide an appealing approach to diffusion inversion for text-guided i…
Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groups
Daniil Shmelev, Luke Thompson, Cristopher Salvi
Backpropagation through (neural) SDE solvers is traditionally approached in two ways: discretise-then-optimise, which offers accurate gradients but incurs prohibitive memory costs;…
Explicit and Effectively Symmetric Runge-Kutta Methods
Daniil Shmelev, Kurusch Ebrahimi-Fard, Nikolas Tapia +1
Symmetry is a key property of numerical methods. The geometric properties of symmetric schemes make them an attractive option for integrating Hamiltonian systems, whilst their abil…
pySigLib -- Fast Signature-Based Computations on CPU and GPU
Daniil Shmelev, Cristopher Salvi
Signature-based methods have recently gained significant traction in machine learning for sequential data. In particular, signature kernels have emerged as powerful discriminators…
Sparse Signature Coefficient Recovery via Kernels
Daniil Shmelev, Cristopher Salvi
Central to rough path theory is the signature transform of a path, an infinite series of tensors given by the iterated integrals of the underlying path. The signature poses an effe…