Zobrazeno 1 - 10
of 147
pro vyhledávání: '"Pottie, Gregory"'
Data poisoning attacks pose a significant threat to the integrity of machine learning models by leading to misclassification of target distribution data by injecting adversarial examples during training. Existing state-of-the-art (SoTA) defense metho
Externí odkaz:
http://arxiv.org/abs/2405.19376
Train-time data poisoning attacks threaten machine learning models by introducing adversarial examples during training, leading to misclassification. Current defense methods often reduce generalization performance, are attack-specific, and impose sig
Externí odkaz:
http://arxiv.org/abs/2405.18627
We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety of image
Externí odkaz:
http://arxiv.org/abs/2303.03462
A vast amount of expert and domain knowledge is captured by causal structural priors, yet there has been little research on testing such priors for generalization and data synthesis purposes. We propose a novel model architecture, Causal Structural H
Externí odkaz:
http://arxiv.org/abs/2210.11275
Variational autoencoders (VAEs) and other generative methods have garnered growing interest not just for their generative properties but also for the ability to dis-entangle a low-dimensional latent variable space. However, few existing generative mo
Externí odkaz:
http://arxiv.org/abs/2207.01575
We propose a cross-layer strategy for resource allocation between spatially correlated sources in the uplink of multi-cell FDMA networks. Our objective is to find the optimum power and channel to sources, in order to minimize the maximum distortion a
Externí odkaz:
http://arxiv.org/abs/1112.2723
In this paper, we investigate the sum-capacity of the two-user Gaussian interference channel with Gaussian superposition coding and successive decoding. We first examine an approximate deterministic formulation of the problem, and introduce the compl
Externí odkaz:
http://arxiv.org/abs/1103.0038
Autor:
Zhao, Yue, Pottie, Gregory J.
In this paper, we study the non-convex problem of continuous frequency optimal spectrum management in multiuser frequency selective interference channels. Firstly, a simple pairwise channel condition for FDMA schemes to achieve all Pareto optimal poi
Externí odkaz:
http://arxiv.org/abs/1102.3758