Adversarial Spheres — mentioned by ericjang

Fri, 22 Nov 2024 17:33:29 GMT

intra-distribution generalization is also not well posed in practical real world settings. suppose you learn a mapping f : x -> y. casually, intra-distribution generalization implies that f generalizes for "points from the same data distribution p(x)". Two issues here: 1. In practical scenarios, how do you know if x' is really drawn from p(x)? Even if you could compute log p(x') under the true data distribution, you can only verify that the support for x' is non-zero. one sample is not enough to tell you if x' drawn from p(x). 2. In high dimensional settings, x' that is not exactly equal to…

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

Adversarial Spheres — HN submission

Wed, 10 Jan 2018 20:27:49 GMT

Adversarial Spheres [pdf]

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

Adversarial Spheres · HackerPapers discussions

Adversarial Spheres — mentioned by ericjang

Adversarial Spheres — HN submission