Topic

Variational Inference (ELBO)

All digests tagged Variational Inference (ELBO)

· 1:22:31

Stanford CS229 Machine Learning | Spring 2026 | Lecture 11: Diffusion Models

The lecture introduces Diffusion Models as a predominant class of generative models used for tasks like image, video, and action generation. The core mechanism involves two processes: the forward process (gradually adding Gaussian noise to an original clean image $X_0$ over time steps $T$) and the reverse process (learning to iteratively denoise the noisy data back to a clean state). Training these models is achieved by applying the Evidence Lower Bound (ELBO) framework, which minimizes the Kullback-Leibler (KL) divergence between the true conditional distribution and the parameterized model's prediction.

Key takeaways

  1. Diffusion Models Overview

    These models are generative frameworks that can be applied to images, videos, and robotics actions. They are noted as a superior approach compared to GANs and Variational Autoencoders (VAEs) for image generation.

  2. Forward vs. Reverse Process 4:05

    The forward process is a fixed, known noising process that transforms $X_0$ to noise $X_T$. The reverse process is the learned component, parameterized by $ heta$, which predicts $p_ heta(X_{t-1}|X_t)$—the step-by-step denoising path.

  3. Training Objective (ELBO) 6:25

    The goal is to maximize the marginal likelihood $ ext{log } p_ heta(X_0)$ by applying the Evidence Lower Bound (ELBO). This involves minimizing the KL divergence between the true posterior $q(X_{t-1}|X_t, X_0)$ and the parameterized model's distribution.

Watch on YouTube Full article