scipy没有进行优化，并返回“由于精度损失，不一定实现所需的错误”

Question

我有以下代码，试图最小化一个日志似然函数。

#!/usr/bin/python
import math
import random
import numpy as np
from scipy.optimize import minimize

def loglikelihood(params, data):
    (mu, alpha, beta) = params
    tlist = np.array(data)
    r = np.zeros(len(tlist))
    for i in xrange(1,len(tlist)):
        r[i] = math.exp(-beta*(tlist[i]-tlist[i-1]))*(1+r[i-1])
    loglik  = -tlist[-1]*mu
    loglik = loglik+alpha/beta*sum(np.exp(-beta*(tlist[-1]-tlist))-1)
    loglik = loglik+np.sum(np.log(mu+alpha*r))
    return -loglik

atimes = [ 148.98894201,  149.70253172,  151.13717804,  160.35968355,
        160.98322609,  161.21331798,  163.60755544,  163.68994973,
        164.26131871,  228.79436067]
a= 0.01
alpha = 0.5
beta = 0.6
print loglikelihood((a, alpha, beta), atimes)

res = minimize(loglikelihood, (0.01, 0.1,0.1), method = 'BFGS',args = (atimes,))
print res

它给了我

28.3136498357
./test.py:17: RuntimeWarning: invalid value encountered in log
  loglik = loglik+np.sum(np.log(mu+alpha*r))
   status: 2
  success: False
     njev: 14
     nfev: 72
 hess_inv: array([[1, 0, 0],
       [0, 1, 0],
       [0, 0, 1]])
      fun: 32.131359359964378
        x: array([ 0.01,  0.1 ,  0.1 ])
  message: 'Desired error not necessarily achieved due to precision loss.'
      jac: array([ -2.8051672 ,  13.06962156, -48.97879982])

注意，它根本没能优化参数，最小值32大于28，这就是a=0.01，alpha=0.5，beta=0.6得到的结果。有可能通过选择更好的初始猜测可以避免这个问题，但如果是这样，我如何能自动做到这一点？

Answer 1

注意log（）函数的负值，通过添加惩罚来解析它们并告诉优化器它们是坏的：

#!/usr/bin/python
import math
import random
import numpy as np
from scipy.optimize import minimize

def loglikelihood(params, data):
    (mu, alpha, beta) = params
    tlist = np.array(data)
    r = np.zeros(len(tlist))
    for i in xrange(1,len(tlist)):
        r[i] = math.exp(-beta*(tlist[i]-tlist[i-1]))*(1+r[i-1])
    loglik = -tlist[-1]*mu
    loglik += alpha/beta*sum(np.exp(-beta*(tlist[-1]-tlist))-1)
    argument = mu + alpha * r
    limit = 1e-6
    if np.min(argument) < limit:
        # add a penalty for too small argument of log
        loglik += np.sum(np.minimum(0.0, argument - limit)) / limit
        # keep argument of log above the limit
        argument = np.maximum(argument, limit)
    loglik += np.sum(np.log(argument))
    return -loglik

atimes = [ 148.98894201,  149.70253172,  151.13717804,  160.35968355,
        160.98322609,  161.21331798,  163.60755544,  163.68994973,
        164.26131871,  228.79436067]
a= 0.01
alpha = 0.5
beta = 0.6
print loglikelihood((a, alpha, beta), atimes)

res = minimize(loglikelihood, (0.01, 0.1,0.1), method = 'BFGS',args = (atimes,))
print res