Sebastien Bubeck   @SebastienBubeck   6/9/2021       

We may have found a solid hypothesis to explain why extreme overparametrization is so helpful in #DeepLearning, especially if one is concerned about adversarial robustness. https://t.co/yyK4IuZvAs 1/7

 Reply  0     Retweet   139      Like   714





Posted by Sebastien Bubeck