Predicting the Generalization Gap in Deep Networks with Margin Distributions — mentioned by choppaface

Sun, 21 Mar 2021 19:04:40 GMT

You're not ablating anything there. What happens when Train Infinity (Train 150K) doubles in size (to Train Infinity_2 -> 300K)? What happens when you add an unseen class? These are real-world conditions that hamper existing theoretical estimation of the generalization gap-- the "ideal world" always gets larger. In Bengio's group paper (Predicting the Generalization Gap https://arxiv.org/pdf/1810.00113.pdf ) they actually do these sorts of ablations. Also, you use K (thousands) and $K$ (latex K) interchangeably; it's really hard to decipher is K is a variable or what you mean.

Paper and discussion history. A mention is not an endorsement.

Predicting the Generalization Gap in Deep Networks with Margin Distributions · HackerPapers discussions

Predicting the Generalization Gap in Deep Networks with Margin Distributions — mentioned by choppaface