@tw_killian
π Happy to hear that you like it!
ODE - base case. A continuous time version of a ResNet.
CDE - when you add in a time-varying input. A continuous time version of an RNN.
SDE - when you want a generative model; think of this like a GAN. Noise goes in, sample comes out.
Iβve been slowly and surely making my way through
@PatrickKidger
βs thesis (itβs remarkable btw):
While Iβve been learning a lot Iβve found it hard to know which type of NDE I want to use. Does anyone know of a clear taxonomy between ODEs, SDEs and CDEs?
@tw_killian
So for example, a CDE may be used to model a function of a time series / path. SDEs can be used to model the distribution time series/ path itself.
Here's another explanation I like giving. Between ODEs amd SDEs there are actually ...
2/n
@tw_killian
...three differences: (1) a control; your diffeq changed its output based on the Brownian input. (2) roughness: Brownian motion is not a bounded variation process. (3) stochasticity: your input Brownian path is random.
This is despite only (3) being reflected in the name!
3/n