Skip to content
masterclass Buddy
Start learning

PyTorch · Class

optim.Adagrad

Adagrad is a PyTorch optimizer that adapts each parameter update using accumulated squared gradients. It also supports learning-rate decay, weight decay, maximization, and alternate implementations.

Last updated

Syntax

class torch.optim.adagrad.Adagrad(params, lr=0.01, lr_decay=0, weight_decay=0, initial_accumulator_value=0, eps=1e-10, foreach=None, *, maximize=False, differentiable=False, fused=None)

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • torch.optim.adagrad.adagrad
  • torch.optim.Optimizer

Source: Adagrad — PyTorch 2.15 documentation. Checked 2026-11-03.