Search Results for author: Pei-Yuan Wu

Found 7 papers, 1 papers with code

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

no code implementations31 Oct 2024 Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih, Pei-Yuan Wu

This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR.

reinforcement-learning Reinforcement Learning

Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning

no code implementations22 Aug 2024 Yen-Ru Lai, Fu-Chieh Chang, Pei-Yuan Wu

This situation highlights the importance of finding effective ways to use unlabelled data in offline RL, especially when labelled data is limited or expensive to obtain.

Offline RL Reinforcement Learning (RL)

CAPM: Fast and Robust Verification on Maxpool-based CNN via Dual Network

no code implementations27 Jun 2024 Jia-Hau Bai, Chi-Ting Liu, Yu Wang, Fu-Chieh Chang, Pei-Yuan Wu

This study uses CAPM (Convex Adversarial Polytope for Maxpool-based CNN) to improve the verified bound for general purpose maxpool-based convolutional neural networks (CNNs) under bounded norm adversarial perturbations.

Sample Complexity of Kernel-Based Q-Learning

no code implementations1 Feb 2023 Sing-Yuan Yeh, Fu-Chieh Chang, Chang-Wei Yueh, Pei-Yuan Wu, Alberto Bernacchia, Sattar Vakili

To the best of our knowledge, this is the first result showing a finite sample complexity under such a general model.

Q-Learning Reinforcement Learning (RL)

CTGAN : Cloud Transformer Generative Adversarial Network

1 code implementation 2022 International Conference on Image Processing (ICIP 2022) 2022 Gi-Luen Huang, Pei-Yuan Wu

Meanwhile, to address the lack of datasets, we collected a new dataset named Sen2 MTC from the Sentinel-2 satellite and manually labeled each cloudy and cloud-free image.

Generative Adversarial Network Land Cover Classification

AutoGAN-based Dimension Reduction for Privacy Preservation

no code implementations27 Feb 2019 Hung Nguyen, Di Zhuang, Pei-Yuan Wu, Morris Chang

Protecting sensitive information against data exploiting attacks is an emerging research area in data mining.

Cryptography and Security

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