{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":480,"html":"<iframe src=\"https://montaan.com/embed/episode/62ab16d4-ff4c-4dd5-9a0e-9c2968a4a86c\" width=\"1280\" height=\"480\" title=\"Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities — 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/62ab16d4-ff4c-4dd5-9a0e-9c2968a4a86c/episode.poster.webp","title":"Theoretical guarantees for stochastic gradient sampling methods via Gaussian convolution inequalities","type":"rich","version":"1.0","width":1280}