Stochastic global optimization using the Metropolis-Szymura-Barton algorithm. New parameters are chosen from a uniform candidate distribution with an adaptively tuned scale, and accepted or rejected according to a Metropolis rule.
metropSB(fn, start, deltap = NULL, scale = 1, rptfreq = -1, acceptscale
= 1.01, rejectscale = 0.99, nmax = 10000,
retvals = FALSE, retfreq = 100, verbose = FALSE, ...)
minimum value achieved
parameters corresponding to minimum
number of function evaluations
If retvals=TRUE:
matrix of periodic samples including parameters, jump scale, current value, and minimum achieved value
Objective function, taking a vector of parameters as its first argument. The function is minimized, so it should be a negative log-likelihood or a negative log-posterior density.
Vector of starting values
Starting jump size; half-width of uniform distribution
Scaling factor for acceptance
Frequency for reporting interim results (<0 means no reporting)
Amount to inflate candidate distribution if last jump was accepted
Amount to shrink candidate distribution if last jump was rejected
Number of iterations
Return detailed statistics?
Sampling frequency for detailed statistics
Print status?
Other arguments to fn
Ben Bolker
Metropolis-Szymura-Barton algorithm: given function and starting value, try to find parameters that minimize the function Algorithm: at a given step, 1. pick a new set of parameters, each of which is uniformly distributed in (p[i]-deltap[i],p[i]+deltap[i]) 2. calculate function value at new parameter values 3. if f(new)<f(old), accept 4. if f(new)>f(old), accept with probability (exp(-scale*(f(new)-f(old))) 5. if accept, increase all deltap values by acceptscale; if reject, decrease by rejectscale 6. if better than min so far, save function and parameter values 7. if reject, restore old values
Szymura and Barton (1986) Genetic analysis of a hybrid zone between the fire-bellied toads,Bombina bombina and B. variegata, near Cracow in southern Poland. Evolution 40(6):1141-1159.
optim, MCMCmetrop1R (MCMCpack package)