Adam

A gradient method using random minibatches for efficient training on large datasets.

Reinforcement learning from human feedback: uses preference data to train a reward model and optimize the policy.

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

Penalizes confident wrong predictions heavily; standard for classification and language modeling.

Average of squared residuals; common regression objective.

Iterative method that updates parameters in the direction of negative gradient to minimize loss.

Uses an exponential moving average of gradients to speed convergence and reduce oscillation.