<iframe src="https://amupod.univ-amu.fr/video/16762-towards-building-a-heavy-tailed-theory-of-stochastic-gradient-descent-for-deep-neural-networks-by-umut-simsekli-inria/?is_iframe=true" width="640" height="360" style="padding: 0; margin: 0; border:0" allowfullscreen loading='lazy'></iframe>
Towards Building a Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks by Umut Simsekli (Inria)
AMUpod
https://amupod.univ-amu.fr/videos/?owner=vemiya
360
https://amupod.univ-amu.fr
video
640
1.0
Valentin EMIYA
https://amupod.univ-amu.fr/media/files/0d90c3c94f13283bb53dd18936e10a98d42b3d446b128f5cb58fa03501c869a2/vignette.png
889
500