CODE = r"""
import torch
from torch.optim import Optimizer


class GradientDescent(Optimizer):
    def __init__(self, params, lr=1e-2):
        if lr < 0:
            raise ValueError(f"Invalid learning rate: {lr}")
        defaults = dict(lr=lr)
        super().__init__(params, defaults)

    @torch.no_grad()
    def step(self, closure=None):
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            lr = group["lr"]
            for p in group["params"]:
                if p.grad is None:
                    continue
                p.add_(p.grad, alpha=-lr)

        return loss


def build_optimizer(params, config):
    return GradientDescent(params, lr=config.get("lr", 1e-2))
"""

DEFAULT_CONFIG = {"lr": 1e-2}
DESCRIPTION = "Plain gradient descent: parameter <- parameter - lr * gradient."