Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Welfert, Monica"'
Ensuring fair predictions across many distinct subpopulations in the training data can be prohibitive for large models. Recently, simple linear last layer retraining strategies, in combination with data augmentation methods such as upweighting, downs
Externí odkaz:
http://arxiv.org/abs/2405.05934
Autor:
Stromberg, Nathan, Ayyagari, Rohan, Welfert, Monica, Koyejo, Sanmi, Nock, Richard, Sankar, Lalitha
Existing methods for last layer retraining that aim to optimize worst-group accuracy (WGA) rely heavily on well-annotated groups in the training data. We show, both in theory and practice, that annotation-based data augmentations using either downsam
Externí odkaz:
http://arxiv.org/abs/2402.11039
Generative adversarial networks (GANs), modeled as a zero-sum game between a generator (G) and a discriminator (D), allow generating synthetic data with formal guarantees. Noting that D is a classifier, we begin by reformulating the GAN value functio
Externí odkaz:
http://arxiv.org/abs/2310.18291
In an effort to address the training instabilities of GANs, we introduce a class of dual-objective GANs with different value functions (objectives) for the generator (G) and discriminator (D). In particular, we model each objective using $\alpha$-los
Externí odkaz:
http://arxiv.org/abs/2302.14320
We prove a two-way correspondence between the min-max optimization of general CPE loss function GANs and the minimization of associated $f$-divergences. We then focus on $\alpha$-GAN, defined via the $\alpha$-loss, which interpolates several GANs (He
Externí odkaz:
http://arxiv.org/abs/2205.06393
We present a data-driven framework for learning fair universal representations (FUR) that guarantee statistical fairness for any learning task that may not be known a priori. Our framework leverages recent advances in adversarial learning to allow a
Externí odkaz:
http://arxiv.org/abs/1910.00411
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.