Course Study Note

Day 2 — Autoregressive Models and MLE

I factorized joint probabilities into conditionals and connected maximum likelihood with negative log-likelihood.

Date
2025-07-08
Course
2025 Generative Models Intensive — From VAE to Stable Diffusion
01Autoregressive Models

Study checkpoint for this day

02Maximum Likelihood Estimation

Study checkpoint for this day

A day-level study path generated from the saved course topic order.

Topics from the day

  1. Autoregressive Models

    I reviewed sequential prediction and teacher forcing.

  2. Maximum Likelihood Estimation

    I followed the conversion from a product of probabilities to a log-sum loss.

Autoregressive sequence and negative log-likelihood
Joint-probability factorization and NLL are two views of the same training path.

Factorizing a joint distribution

(p(x_1, ldots, x_T)=\prod_t p(x_t x_{<t})) turns a high-dimensional problem into next-value prediction. PixelRNN applies this view over two image axes.

Teacher forcing

Training can feed the true prefix, while generation must reuse model samples. Early mistakes can therefore propagate. A causal Transformer uses the same dependency rule even though its training operations are parallelized.

From MLE to a loss

Taking logs turns products into sums. Negating the objective converts maximization into a negative log-likelihood loss; cross entropy selects the log probability assigned to the target class.

The next step was handling a latent variable whose posterior is not directly tractable.

← Course home
Publication first-page preview