Zobrazeno 1 - 10
of 27
pro vyhledávání: '"XU Tianshi"'
Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green's functi
Externí odkaz:
http://arxiv.org/abs/2410.18439
PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
Private deep neural network (DNN) inference based on secure two-party computation (2PC) enables secure privacy protection for both the server and the client. However, existing secure 2PC frameworks suffer from a high inference latency due to enormous
Externí odkaz:
http://arxiv.org/abs/2410.09531
With the fast evolution of large language models (LLMs), privacy concerns with user queries arise as they may contain sensitive information. Private inference based on homomorphic encryption (HE) has been proposed to protect user query privacy. Howev
Externí odkaz:
http://arxiv.org/abs/2405.16241
Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant computation overhead. We observe transforming the DNN weights into circulant matrices converts general matrix-vector mu
Externí odkaz:
http://arxiv.org/abs/2405.14569
Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution layers. In this paper, we propose EQO, a quantized 2PC inference framew
Externí odkaz:
http://arxiv.org/abs/2404.09404
Anderson Acceleration (AA) is a popular algorithm designed to enhance the convergence of fixed-point iterations. In this paper, we introduce a variant of AA based on a Truncated Gram-Schmidt process (AATGS) which has a few advantages over the classic
Externí odkaz:
http://arxiv.org/abs/2403.14961
Secure two-party computation with homomorphic encryption (HE) protects data privacy with a formal security guarantee but suffers from high communication overhead. While previous works, e.g., Cheetah, Iron, etc, have proposed efficient HE-based protoc
Externí odkaz:
http://arxiv.org/abs/2401.15970
Efficient networks, e.g., MobileNetV2, EfficientNet, etc, achieves state-of-the-art (SOTA) accuracy with lightweight computation. However, existing homomorphic encryption (HE)-based two-party computation (2PC) frameworks are not optimized for these n
Externí odkaz:
http://arxiv.org/abs/2308.13189
The spectrum of a kernel matrix significantly depends on the parameter values of the kernel function used to define the kernel matrix. This makes it challenging to design a preconditioner for a regularized kernel matrix that is robust across differen
Externí odkaz:
http://arxiv.org/abs/2304.05460
This paper presents a parallel preconditioning approach based on incomplete LU (ILU) factorizations in the framework of Domain Decomposition (DD) for general sparse linear systems. We focus on distributed memory parallel architectures, specifically,
Externí odkaz:
http://arxiv.org/abs/2303.08881