The Modern Mathematics of Deep Learning · HackerPapers discussions

The Modern Mathematics of Deep Learning — HN submission

Fri, 16 Jun 2023 18:34:27 GMT

The Modern Mathematics of Deep Learning

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

The Modern Mathematics of Deep Learning — mentioned by sinenomine

Tue, 10 Jan 2023 01:22:27 GMT

Ironic, since the relatively recently discovered double descent makes it clear that bias-variance tradeoff as we know it from statistical learning theory simply doesn't apply to "overparameterized" deep models. Much of old theory is barely applicable and people are, understandably, bewildered and in denial. If someone were to be inclined to theory, I'd just recommend reading papers that don't try oversimplify the domain: https://arxiv.org/abs/2006.15191 https://arxiv.org/abs/2210.10749 https://arxiv.org/abs/2205.10343 https://arxiv.org/abs/2105.04026

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

The Modern Mathematics of Deep Learning — HN submission

Sat, 12 Jun 2021 16:37:55 GMT

The Modern Mathematics of Deep Learning

276 points; 70 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Modern Mathematics of Deep Learning — HN submission

Fri, 11 Jun 2021 15:06:38 GMT

The Modern Mathematics of Deep Learning

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

The Modern Mathematics of Deep Learning — HN submission

Wed, 12 May 2021 12:02:35 GMT

The modern mathematics of deep learning

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