Zobrazeno 1 - 10
of 111
pro vyhledávání: '"Yu, Yaoliang"'
Autor:
Wang, Yihan, Lu, Yiwei, Zhang, Guojun, Boenisch, Franziska, Dziedzic, Adam, Yu, Yaoliang, Gao, Xiao-Shan
Machine unlearning provides viable solutions to revoke the effect of certain training data on pre-trained model parameters. Existing approaches provide unlearning recipes for classification and generative models. However, a category of important mach
Externí odkaz:
http://arxiv.org/abs/2406.03603
High utility and rigorous data privacy are of the main goals of a federated learning (FL) system, which learns a model from the data distributed among some clients. The latter has been tried to achieve by using differential privacy in FL (DPFL). Ther
Externí odkaz:
http://arxiv.org/abs/2406.03519
Copyright infringement may occur when a generative model produces samples substantially similar to some copyrighted data that it had access to during the training phase. The notion of access usually refers to including copyrighted samples directly in
Externí odkaz:
http://arxiv.org/abs/2404.06737
In this work, we study potential games and Markov potential games under stochastic cost and bandit feedback. We propose a variant of the Frank-Wolfe algorithm with sufficient exploration and recursive gradient estimation, which provably converges to
Externí odkaz:
http://arxiv.org/abs/2404.06516
Diffusion models have become the leading distribution-learning method in recent years. Herein, we introduce structure-preserving diffusion processes, a family of diffusion processes for learning distributions that possess additional structure, such a
Externí odkaz:
http://arxiv.org/abs/2402.19369
In neural network binarization, BinaryConnect (BC) and its variants are considered the standard. These methods apply the sign function in their forward pass and their respective gradients are backpropagated to update the weights. However, the derivat
Externí odkaz:
http://arxiv.org/abs/2402.17710
Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to self-supervised learning
Externí odkaz:
http://arxiv.org/abs/2402.12626
In self-supervised contrastive learning, a widely-adopted objective function is InfoNCE, which uses the heuristic cosine similarity for the representation comparison, and is closely related to maximizing the Kullback-Leibler (KL)-based mutual informa
Externí odkaz:
http://arxiv.org/abs/2402.10150
Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine learning (ML) ar
Externí odkaz:
http://arxiv.org/abs/2303.03592
Modern machine learning systems achieve great success when trained on large datasets. However, these datasets usually contain sensitive information (e.g. medical records, face images), leading to serious privacy concerns. Differentially private gener
Externí odkaz:
http://arxiv.org/abs/2208.03409