{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/1da41234-e5b1-4477-aa18-96b4ca87f9af\" width=\"1280\" height=\"720\" title=\"Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping — 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://montaan.com/","thumbnail_url":"https://montaan.com/media/episodes/1da41234-e5b1-4477-aa18-96b4ca87f9af/episode.poster.webp","title":"Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping","type":"video","version":"1.0","width":1280}