We propose Electrostatic Field Matching (EFM), a novel method that is suitable for both generative modeling and distribution transfer tasks. Our approach is inspired by the physics of an electrical capacitor. We place source and target distributions on the capacitor plates and assign them positive and negative charges, respectively. We then learn the electrostatic field of the capacitor using a neural network approximator. To map the distributions to each other, we start at one plate of the capacitor and move the samples along the learned electrostatic field lines until they reach the other plate. We theoretically justify that this approach provably yields the distribution transfer. In practice, we demonstrate the performance of our EFM in toy and image data experiments.

A new particle-based sampling and approximate inference method, based on electrostatics and Newton mechanics principles, is introduced with theoretical ground, algorithm design and experimental validation. This method simulates an interacting particle system (IPS) where particles, i.e. the freely-moving negative charges and spatially-fixed positive charges with magnitudes proportional to the target distribution, interact with each other via attraction and repulsion induced by the resulting electric fields described by Poisson's equation. The IPS evolves towards a steady-state where the distribution of negative charges conforms to the target distribution. This physics-inspired method offers deterministic, gradient-free sampling and inference, achieving comparable performance as other particle-based and MCMC methods in benchmark tasks of inferring complex densities, Bayesian logistic regression and dynamical system identification. A discrete-time, discrete-space algorithmic design, readily extendable to continuous time and space, is provided for usage in more general inference problems occurring in probabilistic machine learning scenarios such as Bayesian inference, generative modelling, and beyond.

MIT researchers have created a real life'shrink ray' that can reduce 3D structures to one thousandth of their original size. Scientists can put all kinds of useful materials in the polymer before they shrink it, including metals, quantum dots, and DNA. The process is essentially the opposite of expansion microscopy, which is widely used by scientists to create 3D visualisations of microscopic cells. Instead of making things bigger, scientists attach special molecules which block negative charges between molecules so they no longer repel which makes them contract. Experts say that making such tiny structures could be useful in many fields, including in medicine and for creating nanoscale robotics.

Last week, Stanford researchers revealed that that they had built tiny drones that can open doors. I'm not sure I'm happy about this: How will we keep the robots out of our houses if they can just open the doors? But this is also pretty cool. These tiny drones (or micro air vehicles) are able to pull super heavy loads as compared to their own weight--up to a factor of 40. Well, I guess it's crazy--crazy awesome.