flâneur

[2406.08929] Step-by-Step Diffusion: An Elementary Tutorial

ar5iv.labs.arxiv.org · 25,053 words · saved by 1 readers

colorlinks=true, linkcolor=mydarkblue, citecolor=mydarkblue, filecolor=mydarkblue, urlcolor=mydarkblue, pdfview=FitH, \WarningFilter*latexMarginpar on page 0 moved \WarningFilter*captionThe option ‘hypcap=true’ will be ignored We present an accessible first course on diffusion models and flow matching for machine learning, aimed at a technical audience with no diffusion experience. We try to simplify the mathematical details as much as possible (sometimes heuristically), while retaining enough precision to derive correct algorithms. There are many existing resources for learning diffusion models. Why did we write another? Our goal was to teach diffusion as simply as possible, with minimal mathematical and machine learning prerequisites, but in enough detail to reason about its correctness. Unlike most tutorials on this subject, we take neither a Variational Auto Encoder (VAE) nor an Stochastic Differential Equations (SDE) approach. In fact, for the core ideas we will not need any SDEs,

[2406.08929] Step-by-Step Diffusion: An Elementary Tutorial \hypersetup colorlinks=true, linkcolor=mydarkblue, citecolor=mydarkblue, filecolor=mydarkblue, urlcolor=mydarkblue, pdfview=FitH, \WarningFilter *latexMarginpar on page 0 moved \WarningFilter *captionThe option ‘hypcap=true’ will be ignored Step-by-Step Diffusion: An Elementary Tutorial Preetum Nakkiran 1 Arwen Bradley 1 Hattie Zhou 1,2 Madhu Advani 1 ( 1 Apple, 2 Mila, Université de Montréal) Abstract We present an accessible first course on diffusion models and flow matching for machine learning, aimed at a technical audience with n

saved by

related reading