Realizing GANs via a Tunable Loss Function

2021-06-09 · Gowtham R. Kurri, Tyler Sypherd, Lalitha Sankar

We introduce a tunable GAN, called $\alpha$-GAN, parameterized by $\alpha \in (0,\infty]$, which interpolates between various $f$-GANs and Integral Probability Metric based GANs (under constrained discriminator set). We construct $\alpha$-GAN using a supervised loss function, namely, $\alpha$-loss, which is a tunable loss function capturing several canonical losses. We show that $\alpha$-GAN is intimately related to the Arimoto divergence, which was first proposed by \"{O}sterriecher (1996), and later studied by Liese and Vajda (2006). We also study the convergence properties of $\alpha$-GAN. We posit that the holistic understanding that $\alpha$-GAN introduces will have practical benefits of addressing both the issues of vanishing gradients and mode collapse.

📄 PDF Abstract BibTeX arXiv:2106.05232

Code (0)

등록된 구현이 없습니다.

Addressing GAN Training Instabilities via Tunable Classification Losses

2023-10-27 · Monica Welfert, Gowtham R. Kurri, Kyle Otstot, Lalitha Sankar

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 refor…

Classification

Generalized Dual Discriminator GANs

2025-07-23 · Penukonda Naga Chandana, Tejas Srivastava, Gowtham R. Kurri, V. Lalitha arxiv

Dual discriminator generative adversarial networks (D2 GANs) were introduced to mitigate the problem of mode collapse in generative adversarial networks. In D2 GANs, two discriminators are employed alongside a generator:…

$(α_D,α_G)$-GANs: Addressing GAN Training Instabilities via Dual Objectives

2023-02-28 · Monica Welfert, Kyle Otstot, Gowtham R. Kurri, Lalitha Sankar

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 eac…

A Tunable Loss Function for Binary Classification

2019-02-12 · Tyler Sypherd, Mario Diaz, Lalitha Sankar, Peter Kairouz

We present $\alpha$-loss, $\alpha \in [1,\infty]$, a tunable loss function for binary classification that bridges log-loss ($\alpha=1$) and $0$-$1$ loss ($\alpha = \infty$). We prove that $\alpha$-loss has an equivalent …

Binary Classification Classification General Classification regression

Training a neural network with exciton-polariton optical nonlinearity

2021-07-23 · Andrzej Opala, Riccardo Panico, Vincenzo Ardizzone, Barbara Pietka 외

In contrast to software simulations of neural networks, hardware implementations have often limited or no tunability. While such networks promise great improvements in terms of speed and energy efficiency, their performa…