using OptimizationOptimisers using Optimization loss(θ) = norm((predict(θ) - data_train) .* weights) optf = OptimizationFunction((x, p) -> loss(x), AutoReverseDiff(true)) optprob = OptimizationProblem(optf, θ) opt = Adam(0.05, (1.0, 0.985)) # η: learning rate @time results = Optimization.solve( …

Error with maximum likelihood estimation using Optimization

Specific Domains Optimization (Mathematical)

gdalle March 2, 2025, 7:31am 9

From what I can tell, the closure is the SciMLBase.NonlinearFunction to which DI.pullback is applied?
I’ve taken great care to avoid creating closures in DI when Enzyme is involved.

Topic		Replies	Views
Parameter Estimation of ODE system where the response variables are not the state variables Optimization (Mathematical) question , diffeq	8	1179	August 26, 2022
Neural ODE fitting really slow Machine Learning diffeq , flux , sciml	13	2020	September 11, 2020
Tracking initial condition to optimize starting value too Diffeqflux Specific Domains diffeq , flux	11	1351	July 25, 2019
Differential Equations and Parameter Estimation General Usage	21	3641	July 2, 2019
sciML_train func running but not optimizing New to Julia diffeq , flux , optimization , sciml	5	560	April 14, 2021

Error with maximum likelihood estimation using Optimization

Related topics