c6_sgd.py 文件源码

def sgd(f, x0, step, iterations, postprocessing = None, useSaved = False, PRINT_EVERY = 10):
    """ Stochastic Gradient Descent """
    ANNEAL_EVERY = 20000

    if useSaved:
        start_iter, oldx, state = load_saved_params()
        if start_iter > 0:
            x0 = oldx;
            step *= 0.5 ** (start_iter / ANNEAL_EVERY)

        if state:
            random.setstate(state)

    else:
        start_iter = 0

    x = x0

    if not postprocessing:
        postprocessing = lambda x: x

    expcost = None

    for iter in xrange(start_iter + 1, iterations + 1):

        cost = None

        cost, grad = f(x)
        x -= step * grad

        x = postprocessing(x)

        if iter % PRINT_EVERY == 0:
            if not expcost:
                expcost = cost
            else:
                expcost = .95 * expcost + .05 * cost
            print "iter %d: %f" % (iter, expcost)

        if iter % SAVE_PARAMS_EVERY == 0 and useSaved:
            save_params(iter, x)

        if iter % ANNEAL_EVERY == 0:
            step *= 0.5

    return x