mschauer

[deps]
ArraysOfArrays = "65a8f2f4-9b39-5baf-92e2-a9cc46fdf018"
ForwardDiff = "f6369f11-7733-5829-9624-2563aa707210"
MCMCChains = "c7f686f2-ff18-58e9-bc7b-31028e88f75d"
PDMats = "90014a1f-27ba-587c-ab20-58faa44d9150"
Pathfinder = "b1d3bc72-d0e7-4279-b92f-7fa5d6d2d454"
StructArrays = "09ab397b-f2b6-538f-b94a-2f83cf4a842a"
ZigZagBoomerang = "36347407-b186-4a6a-8c98-4f4567861712"

mschauer

# using naive search
using GLMakie, LinearAlgebra
using StaticArrays
rot(θ) = @SMatrix [cos(θ) -sin(θ); sin(θ) cos(θ) ]
x = [Point2f(0,1), Point2f(1,0), Point2f(3, 0)]

xnew = copy(x)
δ = 0.001
xall = [copy(x)]
i = 1

mschauer

#=
ZigZagBoomerang.jl has implemented something like a priority queue keeping track of 
local minima (or high priority task).

Think of graph where vertices are tasks that are assigned priorities (smaller = higher priority) 
and edges between two tasks indicate if the higher priority task has to be worked on before the
lower priority task (edge) or both can be worked on in parallel (no edge).

It’s thread-safe in the sense that priorities can be updated in different threads 
if one has a proper coloring of the vertices and updates the task of one color in @threads

mschauer

[deps]
ForwardDiff = "f6369f11-7733-5829-9624-2563aa707210"
MCMCChains = "c7f686f2-ff18-58e9-bc7b-31028e88f75d"
MappedArrays = "dbb5928d-eab1-5f90-85c2-b9b0edb7c900"
Pathfinder = "b1d3bc72-d0e7-4279-b92f-7fa5d6d2d454"
ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
SampleChainsDynamicHMC = "6d9fd711-e8b2-4778-9c70-c1dfb499d4c4"
Soss = "8ce77f84-9b61-11e8-39ff-d17a774bf41c"
TupleVectors = "615932cf-77b6-4358-adcd-5b7eba981d7e"

mschauer

module Adamopt

# This is a module implementing vanilla Adam (https://arxiv.org/abs/1412.6980).
export Adam, step!

# Struct containing all necessary info
mutable struct Adam
  theta::AbstractArray{Float64} # Parameter array
  loss::Function                # Loss function
  grad::Function                # Gradient function

mschauer

using Distributions

# Search counter examples in exact arithmetic

xpdf(d::Binomial,k) = binomial(d.n, k)*d.p^k*(1 - d.p)^(d.n - k)

f(x,y) = x*y + (1-x)*(1-y)
   
while true

mschauer

using Random, LinearAlgebra, Distributions, StatsBase
# Linear Algebra of Markov chain

# Example: Weather Markov chain of Oz
S = [:R, :S, :C]
P = [0.5 0.25 0.25
     0.5  0    0.5
     0.25 0.25 0.5]

sum(P[2, :])

mschauer

using Observables, BenchmarkTools, Test

struct StaticObservable{T, Listeners} <: Observables.AbstractObservable{T}
    listeners::Listeners
    val::Base.RefValue{T}
end

StaticObservable(obs::Observable) = StaticObservable(tuple(obs.listeners...), Ref(obs[]))
function StaticObservable(val::Ref, listeners...) 
    _notify(val, listeners)

mschauer

n = 1000
x = range(0, 1, length=n)
ς = 1.5 # noise level

μ = 3*x.*sin.(2pi*x) # periodic signal in time domain
#μ = 6*sqrt.(abs.(x .- 0.5)) # this one is difficult to estimate

# Model: Signal distorted by white noise
y = μ + ς*randn(n)  

mschauer

using Mitosis
using MitosisStochasticDiffEq
import MitosisStochasticDiffEq as MSDE
using StaticArrays, LinearAlgebra
using OrdinaryDiffEq

# Match with B and sigma
B(θ) = [-0.1 0.2θ; -0.2θ -0.1]
beta(θ) = [0.,0.]
Σ(θ) = 0.15*I(2)