Search Results for author: Po-Yu Chen

Found 8 papers, 0 papers with code

A Comprehensive Sustainable Framework for Machine Learning and Artificial Intelligence

no code implementations17 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.

Fairness Meta-Learning +1

Differentially Private Fine-Tuning of Diffusion Models

no code implementations3 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.

Image Generation Memorization +1

Online Personalizing White-box LLMs Generation with Neural Bandits

no code implementations24 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.

Headline Generation

Private Training Set Inspection in MLaaS

no code implementations15 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.

Diversity Fairness +1

Learning to Compensate: A Deep Neural Network Framework for 5G Power Amplifier Compensation

no code implementations15 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.

Image Restoration using Total Variation with Overlapping Group Sparsity

no code implementations13 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.

Image Restoration

Group-Sparse Signal Denoising: Non-Convex Regularization, Convex Optimization

no code implementations23 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.

Denoising Speech Enhancement

Translation-Invariant Shrinkage/Thresholding of Group Sparse Signals

no code implementations29 Mar 2013 Po-Yu Chen, Ivan W. Selesnick

This paper addresses signal denoising when large-amplitude coefficients form clusters (groups).

Blocking Denoising +2

Cannot find the paper you are looking for? You can Submit a new open access paper.