Question

Optim.jl执行许多冗余函数调用。对于具有6个变量和方法LBFGS（）的函数（不提供梯度-我的函数是不易计算梯度以及ForwardDiff和ReverseDiff的定点问题的解决方案，由于某些原因，不适用于我的代码）

它在第一次迭代中调用了39次函数。而且，其中许多函数调用都是在完全相同的输入处求值的。这似乎效率很低-我做错什么了吗？如果没有，我可以采取哪些措施来提高效率？

目前我的代码如下-如果需要更多答案，请告诉我。

function f(x::Vector{Float64})

    modelPar.ρ = x[1]
    modelPar.χI = x[2]
    modelPar.χS = x[3]
    modelPar.χE = x[4] * x[3]
    modelPar.λ = x[5]
    modelPar.ν = x[6]

    f = open("figures/log.txt","a")

    write(f,"Iteration: ρ = $(x[1]); χI = $(x[2]); χS = $(x[3]); 
                        χE = $(x[3] * x[4]); λ = $(x[5]); ν = $(x[6])\n")

    close(f)

    output = computeScore(algoPar,modelPar,guess,targets,weights)

end

initial_x = [ modelPar.ρ;
              modelPar.χI;
              modelPar.χS;
              modelPar.χE / modelPar.χS;
              modelPar.λ;
              modelPar.ν ]

lower = [0.01, 0.1, 0.1, 0.01, 1.001, 0.01]
upper = [0.1, 6, 6, 0.99, 1.5, 0.5]

inner_optimizer = LBFGS()

results = optimize(f,lower,upper,initial_x,Fminbox(inner_optimizer),
         Optim.Options(iterations = 0, store_trace = true, show_trace = true))

跟踪如下

Results of Optimization Algorithm
* Algorithm: Fminbox with L-BFGS
* Starting Point: [0.04,4.0,2.0,0.5,1.05,0.05]
* Minimizer: [0.04,4.0,2.0,0.5,1.05,0.05]
* Minimum: 2.069848e-02
* Iterations: 1
* Convergence: true
  * |x - x'| ≤ 0.0e+00: true 
    |x - x'| = 0.00e+00 
  * |f(x) - f(x')| ≤ 0.0e+00 |f(x)|: true
    |f(x) - f(x')| = 0.00e+00 |f(x)|
  * |g(x)| ≤ 1.0e-08: false 
    |g(x)| = 1.63e-01 
  * Stopped by an increasing objective: false
  * Reached Maximum Number of Iterations: true
* Objective Calls: 1
* Gradient Calls: 1

但是，文件log.txt长39行，具有以下内容：

    Iteration: ρ = 0.04000605545445239; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.03999394454554761; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.000024221817809; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 3.9999757781821903; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0000121109089046; χE = 1.0000060554544523; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 1.9999878890910952; χE = 0.9999939445455476; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0000121109089048; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 0.9999878890910953; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.050006358227175; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.049993641772825; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05000605545445239
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.04999394454554761
    Iteration: ρ = 0.04000605545445239; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.03999394454554761; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.000024221817809; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 3.9999757781821903; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0000121109089046; χE = 1.0000060554544523; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 1.9999878890910952; χE = 0.9999939445455476; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0000121109089048; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 0.9999878890910953; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.050006358227175; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.049993641772825; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05000605545445239
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.04999394454554761
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04000605545445239; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.03999394454554761; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.000024221817809; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 3.9999757781821903; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0000121109089046; χE = 1.0000060554544523; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 1.9999878890910952; χE = 0.9999939445455476; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0000121109089048; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 0.9999878890910953; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.050006358227175; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.049993641772825; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05000605545445239
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.04999394454554761
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05
    Iteration: ρ = 0.04; χI = 4.0; χS = 2.0; χE = 1.0; λ = 1.05; ν = 0.05

这是怎么回事？

Answer 1

1.0e-08相当低。您可以尝试使用g_tol=1.0e-6使其收敛吗？

results = optimize(f, lower, upper, initial_x, Fminbox(inner_optimizer), Optim.Options(iterations=0, store_trace=true, show_trace=true, g_tol=1.0e-6))

Optim.jl每次迭代都会进行许多冗余的函数调用

1 个答案: