Balestriero, RandallIbrahim, MarkSobal, VladMorcos, AriShekhar, ShashankGoldstein, TomBordes, FlorianBardes, AdrienMialon, GregoireTian, YuandongSchwarzschild, AviWilson, Andrew GordonGeiping, JonasGarrido, QuentinFernandez, PierreBar, AmirPirsiavash, HamedLeCun, YannGoldblum, Micah2023-11-092023-11-092023-06-28https://doi.org/10.48550/arXiv.2304.12210http://hdl.handle.net/11603/30640Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook. We hope to empower the curious researcher to navigate the terrain of methods, understand the role of the various knobs, and gain the know-how required to explore how delicious SSL can be.71 pagesen-USThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.Text