{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/54a86e02-f2eb-4e51-960c-ad89c15966b5\" width=\"1280\" height=\"720\" title=\"The Computational Advantage of Depth: Learning High-Dimensional Hierarchical Functions with Gradient Descent — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/54a86e02-f2eb-4e51-960c-ad89c15966b5/episode.poster.webp","title":"The Computational Advantage of Depth: Learning High-Dimensional Hierarchical Functions with Gradient Descent","type":"video","version":"1.0","width":1280}