CNF Layer Functions
The following layers are helper functions for easily building neural differential equation architectures specialized for the task of density estimation through Continuous Normalizing Flows (CNF).
DiffEqFlux.FFJORD
— TypeFFJORD(model, tspan, input_dims, args...; ad = nothing, basedist = nothing, kwargs...)
Constructs a continuous-time recurrent neural network, also known as a neural ordinary differential equation (neural ODE), with fast gradient calculation via adjoints [1] and specialized for density estimation based on continuous normalizing flows (CNF) [2] with a stochastic approach [2] for the computation of the trace of the dynamics' jacobian. At a high level this corresponds to the following steps:
- Parameterize the variable of interest x(t) as a function f(z, θ, t) of a base variable z(t) with known density p_z.
- Use the transformation of variables formula to predict the density p_x as a function of the density p_z and the trace of the Jacobian of f.
- Choose the parameter θ to minimize a loss function of p_x (usually the negative likelihood of the data).
After these steps one may use the NN model and the learned θ to predict the density p_x for new values of x.
Arguments:
model
: AFlux.Chain
orLux.AbstractLuxLayer
neural network that defines the dynamics of the model.basedist
: Distribution of the base variable. Set to the unit normal by default.input_dims
: Input Dimensions of the model.tspan
: The timespan to be solved on.args
: Additional arguments splatted to the ODE solver. See the Common Solver Arguments documentation for more details.ad
: The automatic differentiation method to use for the internal jacobian trace. Defaults toAutoForwardDiff()
if full jacobian needs to be computed, i.e.monte_carlo = false
. Else we useAutoZygote()
.kwargs
: Additional arguments splatted to the ODE solver. See the Common Solver Arguments documentation for more details.
References:
[1] Pontryagin, Lev Semenovich. Mathematical theory of optimal processes. CRC press, 1987.
[2] Chen, Ricky TQ, Yulia Rubanova, Jesse Bettencourt, and David Duvenaud. "Neural ordinary differential equations." In Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 6572-6583. 2018.
[3] Grathwohl, Will, Ricky TQ Chen, Jesse Bettencourt, Ilya Sutskever, and David Duvenaud. "Ffjord: Free-form continuous dynamics for scalable reversible generative models." arXiv preprint arXiv:1810.01367 (2018).
DiffEqFlux.FFJORDDistribution
— TypeFFJORD can be used as a distribution to generate new samples by rand
or estimate densities by pdf
or logpdf
(from Distributions.jl
).
Arguments:
model
: A FFJORD instance.regularize
: Whether we use regularization (default:false
).monte_carlo
: Whether we use monte carlo (default:true
).