Zobrazeno 1 - 10
of 5 627
pro vyhledávání: '"Chi, Hua"'
In the current era of big data and machine learning, it's essential to find ways to shrink the size of training dataset while preserving the training performance to improve efficiency. However, the challenge behind it includes providing practical way
Externí odkaz:
http://arxiv.org/abs/2410.09311
Autor:
Tan, Wei, Liu, Wei-Xin, Chen, Ying-Xin, Zhou, Chi-Hua, Zhao, Guo-Dong, Chang, Hong, Wang, Tao
Manipulating quantum states is at the heart of quantum information processing and quantum metrology. Landau-Zener Rabi oscillation (LZRO), which arises from a quantum two-level system swept repeatedly across the avoided crossing point in the time dom
Externí odkaz:
http://arxiv.org/abs/2408.09922
The evaluation of synthetic data generation is crucial, especially in the retail sector where data accuracy is paramount. This paper introduces a comprehensive framework for assessing synthetic retail data, focusing on fidelity, utility, and privacy.
Externí odkaz:
http://arxiv.org/abs/2406.13130
The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. In evaluating these models, a variety of methods have been proposed to
Externí odkaz:
http://arxiv.org/abs/2406.13012
Autor:
Wang, Chi-Hua, Cheng, Guang
We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt the model's
Externí odkaz:
http://arxiv.org/abs/2405.15979
With the proliferation of generative AI and the increasing volume of generative data (also called as synthetic data), assessing the fidelity of generative data has become a critical concern. In this paper, we propose a discriminative approach to esti
Externí odkaz:
http://arxiv.org/abs/2405.15337
Devising procedures for downstream task-oriented generative model selections is an unresolved problem of practical importance. Existing studies focused on the utility of a single family of generative models. They provided limited insights on how synt
Externí odkaz:
http://arxiv.org/abs/2401.00974
Exploring generative model training for synthetic tabular data, specifically in sequential contexts such as credit card transaction data, presents significant challenges. This paper addresses these challenges, focusing on attaining both high fidelity
Externí odkaz:
http://arxiv.org/abs/2401.00965