Search Results for author:
Found 6 papers, 0 papers with code
Theoretical Guarantees of Data Augmented Last Layer Retraining Methods
Ensuring fair predictions across many distinct subpopulations in the training data can be prohibitive for large models.
Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains
Existing methods for last layer retraining that aim to optimize worst-group accuracy (WGA) rely heavily on well-annotated groups in the training data.
Addressing GAN Training Instabilities via Tunable Classification Losses
Generalizing this dual-objective formulation using CPE losses, we define and obtain upper bounds on an appropriately defined estimation error.
$(α_D,α_G)$-GANs: Addressing GAN Training Instabilities via Dual Objectives
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).
$α$-GAN: Convergence and Estimation Guarantees
We prove a two-way correspondence between the min-max optimization of general CPE loss function GANs and the minimization of associated $f$-divergences.
Generating Fair Universal Representations using Adversarial Models
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.
