Bayesian Deep Learning and a Probabilistic Perspective of Generalization — mentioned by yldedly

Tue, 21 Sep 2021 18:43:43 GMT

DD disappears when doing Bayesian model averaging: https://arxiv.org/pdf/2002.08791.pdf It seems DD is a phenomenon specific to point estimates. >overfitting problem is really in terms of model flexibility versus data complexity, and not necessarily in terms of number of parameters per se versus sample size Yep, well put.

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

Bayesian Deep Learning and a Probabilistic Perspective of Generalization — HN submission

Fri, 21 Feb 2020 19:32:01 GMT

Bayesian Deep Learning and a Probabilistic Perspective of Generalization

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Bayesian Deep Learning and a Probabilistic Perspective of Generalization · HackerPapers discussions

Bayesian Deep Learning and a Probabilistic Perspective of Generalization — mentioned by yldedly

Bayesian Deep Learning and a Probabilistic Perspective of Generalization — HN submission