Zobrazeno 1 - 10
of 752
pro vyhledávání: '"Wang, Yu‐xiang"'
Autor:
Zhao, Xuandong, Gunn, Sam, Christ, Miranda, Fairoze, Jaiden, Fabrega, Andres, Carlini, Nicholas, Garg, Sanjam, Hong, Sanghyun, Nasr, Milad, Tramer, Florian, Jha, Somesh, Li, Lei, Wang, Yu-Xiang, Song, Dawn
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of distinguishing between
Externí odkaz:
http://arxiv.org/abs/2411.18479
Mobile devices such as smartphones, laptops, and tablets can often connect to multiple access networks (e.g., Wi-Fi, LTE, and 5G) simultaneously. Recent advancements facilitate seamless integration of these connections below the transport layer, enha
Externí odkaz:
http://arxiv.org/abs/2411.04138
Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying entire doc
Externí odkaz:
http://arxiv.org/abs/2410.03600
We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK) are provably sub-optimal and benign overfitting does not happen, thus
Externí odkaz:
http://arxiv.org/abs/2406.06838
A recent study by De et al. (2022) has reported that large-scale representation learning through pre-training on a public dataset significantly enhances differentially private (DP) learning in downstream tasks, despite the high dimensionality of the
Externí odkaz:
http://arxiv.org/abs/2405.08920
Autor:
Qiao, Dan, Wang, Yu-Xiang
We study the problem of multi-agent reinforcement learning (multi-agent RL) with differential privacy (DP) constraints. This is well-motivated by various real-world applications involving sensitive data, where it is critical to protect users' private
Externí odkaz:
http://arxiv.org/abs/2404.07559
Autor:
Golatkar, Aditya, Achille, Alessandro, Zancato, Luca, Wang, Yu-Xiang, Swaminathan, Ashwin, Soatto, Stefano
Retrieval Augmented Generation (RAG) is emerging as a flexible and robust technique to adapt models to private users data without training, to handle credit attribution, and to allow efficient machine unlearning at scale. However, RAG techniques for
Externí odkaz:
http://arxiv.org/abs/2403.18920
Private selection mechanisms (e.g., Report Noisy Max, Sparse Vector) are fundamental primitives of differentially private (DP) data analysis with wide applications to private query release, voting, and hyperparameter tuning. Recent work (Liu and Talw
Externí odkaz:
http://arxiv.org/abs/2402.06701
In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder. It enjoys robustness properties similar to the standard sampling decoder, but is provably up to 2x better in its quality-robustness tradeoff than sampling and never
Externí odkaz:
http://arxiv.org/abs/2402.05864
This paper addresses the prevalent issue of label shift in an online setting with missing labels, where data distributions change over time and obtaining timely labels is challenging. While existing methods primarily focus on adjusting or updating th
Externí odkaz:
http://arxiv.org/abs/2402.03545