4 papers
Revisiting GAN with Bayes-Optimal Discrimination
Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad +2
We propose an alternative to the standard GAN training approach, in which the discriminator is a binary classifier trained by cross-entropy to distinguish real samples from generat…
Regularized Top-: A Bayesian Framework for Gradient Sparsification
Ali Bereyhi, Ben Liang, Gary Boudreau +1
Error accumulation is effective for gradient sparsification in distributed settings: initially-unselected gradient entries are eventually selected as their accumulated error exceed…
Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
Shayan Mohajer Hamidi, En-Hui Yang, Ben Liang
Inverse problems, where the goal is to recover an unknown signal from noisy or incomplete measurements, are central to applications in medical imaging, remote sensing, and computat…
Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy
Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad +2
This work invokes the notion of -divergence to introduce a novel upper bound on the Bayes error rate of a general classification task. We show that the proposed bound can be com…