Gradient Descent

Direction of steepest ascent of a function.

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

Controls the size of parameter updates; too high diverges, too low trains slowly or gets stuck.

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

Popular optimizer combining momentum and per-parameter adaptive step sizes via first/second moment estimates.

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.

A scalar measure optimized during training, typically expected loss over data, sometimes with regularization terms.

Minimizing average loss on training data; can overfit when data is limited or biased.

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

Average of squared residuals; common regression objective.