DDIM does: deterministic sampling for faster generation with fewer steps

gradient accumulation simulates larger batch sizes without more memory

Can you train a machine like you do with a computer?

batch size affects generalization: larger batches find sharper minima

Larger batch sizes lead to sharper minima, enhancing generalization by providing more accurate gradient estimates

Stable Diffusion

Stable Diffusion generates images from text descriptions

Triton auto-tunes BLOCK_SIZE: different sizes optimize for different hardware

Rate-distortion optimization balances video quality and file size

rejection sampling does: samples from target by accepting/rejecting proposals

Rejection sampling generates observations from a target distribution

Flashbulb memory

Flashbulb memories are vivid but not always accurate