no code implementations • 17 Jul 2024 • Roberto Pagliari, Peter Hill, Po-Yu Chen, Maciej Dabrowny, Tingsheng Tan, Francois Buet-Golfouse
Based on the FPIG framework, we propose a meta-learning algorithm to estimate the four key pillars given a dataset summary, model architecture, and hyperparameters before model training.
no code implementations • 3 Jun 2024 • Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen, Chia-Mu Yu, Xuebin Ren, Francois Buet-Golfouse
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks.
no code implementations • 24 Apr 2024 • Zekai Chen, Weeden Daniel, Po-Yu Chen, Francois Buet-Golfouse
The advent of personalized content generation by LLMs presents a novel challenge: how to efficiently adapt text to meet individual preferences without the unsustainable demand of creating a unique model for each user.
no code implementations • 15 May 2023 • Mingxue Xu, Tongtong Xu, Po-Yu Chen
In this case, the training datasets are typically a private possession of the ML or data companies and are inaccessible to the customers, but the customers still need an approach to confirm that the training datasets meet their expectations and fulfil regulatory measures like fairness.
no code implementations • 15 Jun 2021 • Po-Yu Chen, Hao Chen, Yi-Min Tsai, Hsien-Kai Kuo, Hantao Huang, Hsin-Hung Chen, Sheng-Hong Yan, Wei-Lun Ou, Chia-Ming Cheng
In the proposed framework, Deep Neural Networks (DNNs) are used to learn the characteristics of the PAs, while, correspondent Digital Pre-Distortions (DPDs) are also learned to compensate for the nonlinear and memory effects of PAs.
no code implementations • 13 Oct 2013 • Jun Liu, Ting-Zhu Huang, Ivan W. Selesnick, Xiao-Guang Lv, Po-Yu Chen
Usually, the high-order total variation (HTV) regularizer is an good option except its over-smoothing property.
no code implementations • 23 Aug 2013 • Po-Yu Chen, Ivan W. Selesnick
Convex optimization with sparsity-promoting convex regularization is a standard approach for estimating sparse signals in noise.
no code implementations • 29 Mar 2013 • Po-Yu Chen, Ivan W. Selesnick
This paper addresses signal denoising when large-amplitude coefficients form clusters (groups).