{"id":238758,"date":"2026-06-11T15:05:11","date_gmt":"2026-06-11T20:05:11","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2026\/06\/the-puzzling-success-of-overparameterization-lottery-tickets-or-escape-dimensions"},"modified":"2026-06-11T15:05:11","modified_gmt":"2026-06-11T20:05:11","slug":"the-puzzling-success-of-overparameterization-lottery-tickets-or-escape-dimensions","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2026\/06\/the-puzzling-success-of-overparameterization-lottery-tickets-or-escape-dimensions","title":{"rendered":"The Puzzling Success of Overparameterization: Lottery Tickets or Escape Dimensions?"},"content":{"rendered":"<p><a class=\"blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/the-puzzling-success-of-overparameterization-lottery-tickets-or-escape-dimensions.jpg\"><\/a><\/p>\n<p>Lotteries and tickets are often used as a didactical analogy to explain the success of overparameterized neural networks: \u201clarger networks succeed because they more likely contain a well-initialized subnetwork that can learn the task in isolation, much like buying more tickets increases the chances of winning a lottery.\u201d<\/p>\n<p>This explanation is intuitive but misleading: it suggests that subnetworks can be treated in isolation from the rest of the network. Following this reasoning leads to interpreting learning in wide networks as a multi-start optimization process, where gradient descent simply conducts a parallel search over subnetworks. We argue that this view is flawed since, among other reasons, winning tickets can be made to fail by perturbing the rest of the network.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Lotteries and tickets are often used as a didactical analogy to explain the success of overparameterized neural networks: \u201clarger networks succeed because they more likely contain a well-initialized subnetwork that can learn the task in isolation, much like buying more tickets increases the chances of winning a lottery.\u201d This explanation is intuitive but misleading: it [\u2026]<\/p>\n","protected":false},"author":661,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-238758","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/238758","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/661"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=238758"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/238758\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=238758"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=238758"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=238758"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}