未知
gdprox的Python项目详细描述
H2> GdPROX,近端梯度下降算法
实现了复合目标函数的近端梯度下降算法,即形式{{CD1>}的函数,其中F是光滑函数,G是一个可能的非光滑函数。
这个包的主要功能是gdprox.fmin_cgprox
。此函数遵循与scipy.optimize
中的函数相似的接口。此函数的定义是:
deffmin_cgprox(f,fprime,g_prox,x0,rtol=1e-6,maxiter=1000,verbose=0,default_step_size=1.):""" proximal gradient-descent solver for optimization problems of the form minimize_x f(x) + g(x) where f is a smooth function and g is a (possibly non-smooth) function for which the proximal operator is known. Parameters ---------- f : callable f(x) returns the value of f at x. f_prime : callable f_prime(x) returns the gradient of f. g_prox : callable of the form g_prox(x, alpha) g_prox(x, alpha) returns the proximal operator of g at x with parameter alpha. x0 : array-like Initial guess maxiter : int Maximum number of iterations. verbose : int Verbosity level, from 0 (no output) to 2 (output on each iteration) default_step_size : float Starting value for the line-search procedure. Returns ------- res : OptimizeResult The optimization result represented as a ``scipy.optimize.OptimizeResult`` object. Important attributes are: ``x`` the solution array, ``success`` a Boolean flag indicating if the optimizer exited successfully and ``message`` which describes the cause of the termination. See `scipy.optimize.OptimizeResult` for a description of other attributes. """