1 code implementation • 13 Apr 2024 • Xiwei Cheng, Kexin Fu, Farzan Farnia
In this work, we study the generalization performance of adversarial training methods using the algorithmic stability framework.
1 code implementation • 6 Apr 2024 • Shizhan Gong, Qi Dou, Farzan Farnia
We show a duality relation between the regularized norms of the adversarial perturbations and gradient-based maps, based on which we design adversarial training loss functions promoting sparsity and group-sparsity properties in simple gradient maps.
no code implementations • 15 Mar 2024 • Zixiao Wang, Yunheng Shen, Xufeng Yao, Wenqian Zhao, Yang Bai, Farzan Farnia, Bei Yu
Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention.
no code implementations • 28 Feb 2024 • Haoyu Lei, Amin Gohari, Farzan Farnia
Finally, we present several numerical results on the application of DP-based learning methods to standard centralized and distributed learning problems.
no code implementations • 27 Feb 2024 • Jingwei Zhang, Cheuk Ting Li, Farzan Farnia
The massive developments of generative model frameworks and architectures require principled methods for the evaluation of a model's novelty compared to a reference dataset or baseline generative models.
no code implementations • 10 Jan 2024 • Xiaoyan Hu, Farzan Farnia, Ho-fung Leung
Reinforcement learning (RL) problems where the learner attempts to infer an unobserved reward from some feedback variables have been studied in several recent papers.
no code implementations • 20 Nov 2023 • Yulai Zhao, Wenhao Zhan, Xiaoyan Hu, Ho-fung Leung, Farzan Farnia, Wen Sun, Jason D. Lee
We study CVaR RL in low-rank MDPs with nonlinear function approximation.
no code implementations • 18 Oct 2023 • Zixiao Wang, Farzan Farnia, Zhenghao Lin, Yunheng Shen, Bei Yu
First, we focus on the Fr\'echet inception distance (FID) and consider the following FID-based aggregate scores over the clients: 1) FID-avg as the mean of clients' individual FID scores, 2) FID-all as the FID distance of the trained model to the collective dataset containing all clients' data.
no code implementations • 23 Mar 2023 • Zixiao Wang, Yunheng Shen, Wenqian Zhao, Yang Bai, Guojin Chen, Farzan Farnia, Bei Yu
Deep generative models dominate the existing literature in layout pattern generation.
1 code implementation • ICCV 2023 • Jingwei Zhang, Farzan Farnia
Explaining the predictions of deep neural nets has been a topic of great interest in the computer vision literature.
no code implementations • 30 Nov 2022 • Haniyeh Ehsani Oskouie, Farzan Farnia
Interpreting neural network classifiers using gradient-based saliency maps has been extensively studied in the deep learning literature.
no code implementations • 28 Oct 2022 • Ching Lam Choi, Farzan Farnia
Despite their great success in image recognition tasks, deep neural networks (DNNs) have been observed to be susceptible to universal adversarial perturbations (UAPs) which perturb all input samples with a single perturbation vector.
no code implementations • 3 Jul 2022 • Haochuan Li, Farzan Farnia, Subhro Das, Ali Jadbabaie
In this paper, we aim to bridge this gap by analyzing the \emph{local convergence} of general \emph{nonconvex-nonconcave} minimax problems.
no code implementations • 18 Jun 2022 • Yilin Wang, Farzan Farnia
We support our theoretical results by performing several numerical experiments showing the role of the substitute network's generalization in generating transferable adversarial examples.
no code implementations • 6 Jun 2022 • Farzan Farnia, Amirhossein Reisizadeh, Ramtin Pedarsani, Ali Jadbabaie
In this paper, we focus on this problem and propose a novel personalized Federated Learning scheme based on Optimal Transport (FedOT) as a learning algorithm that learns the optimal transport maps for transferring data points to a common distribution as well as the prediction model under the applied transport map.
no code implementations • 18 Jun 2021 • Farzan Farnia, Amirali Aghazadeh, James Zou, David Tse
Robust training methods against perturbations to the input data have received great attention in the machine learning literature.
1 code implementation • 14 Jun 2021 • Theo Diamandis, Yonina C. Eldar, Alireza Fallah, Farzan Farnia, Asuman Ozdaglar
We propose an optimal transport-based framework for MLR problems, Wasserstein Mixed Linear Regression (WMLR), which minimizes the Wasserstein distance between the learned and target mixture regression models.
no code implementations • 23 Oct 2020 • Farzan Farnia, Asuman Ozdaglar
In this paper, we show that the optimization algorithm also plays a key role in the generalization performance of the trained minimax model.
no code implementations • 18 Jun 2020 • Farzan Farnia, William Wang, Subhro Das, Ali Jadbabaie
Motivated by optimal transport theory, we design the zero-sum game in GAT-GMM using a random linear generator and a softmax-based quadratic discriminator architecture, which leads to a non-convex concave minimax optimization problem.
no code implementations • NeurIPS 2020 • Amirhossein Reisizadeh, Farzan Farnia, Ramtin Pedarsani, Ali Jadbabaie
In such settings, the training data is often statistically heterogeneous and manifests various distribution shifts across users, which degrades the performance of the learnt model.
no code implementations • ICML 2020 • Farzan Farnia, Asuman Ozdaglar
We discuss several numerical experiments demonstrating the existence of proximal equilibrium solutions in GAN minimax problems.
1 code implementation • ICLR 2019 • Farzan Farnia, Jesse M. Zhang, David Tse
A significant portion of this gap can be attributed to the decrease in generalization performance due to adversarial training.
no code implementations • NeurIPS 2018 • Farzan Farnia, David Tse
For a convex set $\mathcal{F}$, this duality framework interprets the original GAN formulation as finding the generative model with minimum JS-divergence to the distributions penalized to match the moments of the data distribution, with the moments specified by the discriminators in $\mathcal{F}$.
no code implementations • ICLR 2018 • Farzan Farnia, Jesse Zhang, David Tse
The recent success of deep neural networks stems from their ability to generalize well on real data; however, Zhang et al. have observed that neural networks can easily overfit random labels.
no code implementations • ICLR 2018 • Soheil Feizi, Farzan Farnia, Tony Ginart, David Tse
Generative Adversarial Networks (GANs) have become a popular method to learn a probability model from data.
1 code implementation • NeurIPS 2016 • Farzan Farnia, David Tse
Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $\Gamma$ on $(X, Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $\Gamma$?
no code implementations • NeurIPS 2015 • Meisam Razaviyayn, Farzan Farnia, David Tse
We prove that for a given set of marginals, the minimum Hirschfeld-Gebelein-Renyi (HGR) correlation principle introduced in [1] leads to a randomized classification rule which is shown to have a misclassification rate no larger than twice the misclassification rate of the optimal classifier.