GP posterior mean with squared-exponential kernel.

GP posterior mean with squared-exponential kernel.

Usage

morie_ghosal_gp_squared_exponential(
  x,
  y,
  length_scale = NULL,
  sigma_f = 1,
  noise = NULL,
  x_star = NULL
)

Arguments

x

Numeric vector or matrix of input points.

y

Numeric response vector.

length_scale

Optional kernel length-scale.

sigma_f

Numeric signal sd (default 1).

noise

Optional observation noise sd.

x_star

Optional matrix of prediction points (defaults to x).

Value

Named list with estimate, se, mu, sd, length_scale, noise, n, method.

Examples

morie_ghosal_gp_squared_exponential(x = rnorm(50), y = rnorm(50))
#> $estimate
#> [1] -0.1926356
#> 
#> $se
#> [1] 0.03354191
#> 
#> $mu
#>  [1] -0.2335052207 -0.3165929859 -0.0149715019 -0.2303578052 -1.5562082264
#>  [6]  0.0361407381 -0.0370991902 -0.0820438510  0.0361905355  0.0281402108
#> [11] -0.0321148020 -0.0892803490 -0.1325070289 -0.1080927743 -0.2907759945
#> [16] -0.3748987541 -0.0032545560  0.0357907811 -0.6840458029 -0.2943305128
#> [21]  0.0246959051  0.0389828502 -0.0525083444 -0.2278967788 -0.2980802815
#> [26] -0.3211393188 -0.3095911715  0.0372254629 -0.0280756119 -1.3731025083
#> [31]  0.0198281744 -0.2301456901  0.0375877009 -0.3422021049  0.0391172604
#> [36]  0.0302717490 -0.2580879304 -0.2251987697 -0.0443593912 -0.7396615589
#> [41] -0.2873621270 -0.2756689034  0.0394089064 -0.2794147125 -0.0001029153
#> [46] -0.2585642790  0.0051917292  0.0111772181 -0.0311219021  0.0108367044
#> 
#> $sd
#>  [1] 0.04095101 0.03267935 0.02744939 0.03366059 0.09249545 0.02544212
#>  [7] 0.02626638 0.02698002 0.02543695 0.02450340 0.02622443 0.02714797
#> [13] 0.02840330 0.02764464 0.03142944 0.04164694 0.02611162 0.02427425
#> [19] 0.08541554 0.03505197 0.02469461 0.02497270 0.02984880 0.03747556
#> [25] 0.04828754 0.03298208 0.03992513 0.02430754 0.02832852 0.07801708
#> [31] 0.02500211 0.03370369 0.02526287 0.03477447 0.02451958 0.02440316
#> [37] 0.03349751 0.03515783 0.02634094 0.05069288 0.03476121 0.03111199
#> [43] 0.02469693 0.03115756 0.02640540 0.03351836 0.02610296 0.02609135
#> [49] 0.02621696 0.02562352
#> 
#> $length_scale
#> [1] 0.8940647
#> 
#> $noise
#> [1] 0.09429863
#> 
#> $n
#> [1] 50
#> 
#> $method
#> [1] "GP regression (squared-exponential kernel)"
#>