Zobrazeno 1 - 10
of 109
pro vyhledávání: '"Wu, Jiafei"'
The development of Large Language Models (LLMs) has significantly advanced various AI applications in commercial and scientific research fields, such as scientific literature summarization, writing assistance, and knowledge graph construction. Howeve
Externí odkaz:
http://arxiv.org/abs/2410.12130
We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting in a superf
Externí odkaz:
http://arxiv.org/abs/2408.09891
Nonparametric contextual bandit is an important model of sequential decision making problems. Under $\alpha$-Tsybakov margin condition, existing research has established a regret bound of $\tilde{O}\left(T^{1-\frac{\alpha+1}{d+2}}\right)$ for bounded
Externí odkaz:
http://arxiv.org/abs/2408.09655
User-level privacy is important in distributed systems. Previous research primarily focuses on the central model, while the local models have received much less attention. Under the central model, user-level DP is strictly stronger than the item-leve
Externí odkaz:
http://arxiv.org/abs/2405.17079
Autor:
Ji, Lichuan, Lin, Yingqi, Huang, Zhenhua, Han, Yan, Xu, Xiaogang, Wu, Jiafei, Wang, Chong, Liu, Zhe
The development of AI-Generated Content (AIGC) has empowered the creation of remarkably realistic AI-generated videos, such as those involving Sora. However, the widespread adoption of these models raises concerns regarding potential misuse, includin
Externí odkaz:
http://arxiv.org/abs/2405.15343
Label differential privacy (DP) is a framework that protects the privacy of labels in training datasets, while the feature vectors are public. Existing approaches protect the privacy of labels by flipping them randomly, and then train a model to make
Externí odkaz:
http://arxiv.org/abs/2405.15150
The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL). However, such a collection manner poses a privacy threat, and one potential solution is Fe
Externí odkaz:
http://arxiv.org/abs/2405.13746
Privacy protection of users' entire contribution of samples is important in distributed systems. The most effective approach is the two-stage scheme, which finds a small interval first and then gets a refined estimate by clipping samples into the int
Externí odkaz:
http://arxiv.org/abs/2405.13453
Autor:
Tao, Chenchen, Peng, Xiaohao, Wang, Chong, Wu, Jiafei, Zhao, Puning, Wang, Jun, Qian, Jiangbo
Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. However, the ambiguous nature of anomaly definitions acr
Externí odkaz:
http://arxiv.org/abs/2403.01169
In existing Video Frame Interpolation (VFI) approaches, the motion estimation between neighboring frames plays a crucial role. However, the estimation accuracy in existing methods remains a challenge, primarily due to the inherent ambiguity in identi
Externí odkaz:
http://arxiv.org/abs/2312.15868