25 Nov 2024

Extending Discrete Laplacian to Non-Manifold Structures

A simple way to construct the discrete Laplacian operator for messy point clouds and non-manifold meshes.

#math #geometry #point-clouds #graph #mesh

29 Jun 2022

The Back-Gradient Trick

Stochastic Gradient Descent can be (kind of) reversed and can be used to compute gradients with respect to its hyperparameters.

#math #ml #gradient #graph #code #jax #deep-learning

27 Jun 2021

A Beautiful Way to Characterize Directed Acyclic Graphs

An interesting connection between the number of cycles in a digraph and its power adjacency matrix leads to a beautiful formulation for DAG constrains.

#graph #math #ml