Ordering of bullet points indicates (rough) chronological order of implementation.
- More GAS distributions – Poisson/Binomial/Gamma/Exponential distributions
- GAS optimization fix – optimization is currently very unreliable for GAS models; intend to implement a custom optimization routine.
- Explanatory variable inclusion for ARIMA/GAS
- VAR models
- Linear/gaussian state space models
- Gaussian process AR/GAS models
- Kernel AR/GAS models
- Hamiltonian Monte Carlo – skeleton of code is complete; need to implement automatic differentiation.
- Black Box Variational Inference
- SGD & AdaGrad
- Expectation Propagation
- Simulation samplers for state space models
- Laplace approximation – use analytical pdf for graphs.
- Prediction intervals – include model uncertainty if using Bayesian inference.
- Conditional least squares option for ARMA models