Zobrazeno 1 - 10
of 490
pro vyhledávání: '"KONG Weiwei"'
Autor:
Amin, Kareem, Bie, Alex, Kong, Weiwei, Kurakin, Alexey, Ponomareva, Natalia, Syed, Umar, Terzis, Andreas, Vassilvitskii, Sergei
We present an approach for generating differentially private synthetic text using large language models (LLMs), via private prediction. In the private prediction framework, we only require the output synthetic data to satisfy differential privacy gua
Externí odkaz:
http://arxiv.org/abs/2407.12108
Autor:
Kong, Weiwei, Ribero, Mónica
Differentially private stochastic gradient descent (DP-SGD) refers to a family of optimization algorithms that provide a guaranteed level of differential privacy (DP) through DP accounting techniques. However, current accounting techniques make assum
Externí odkaz:
http://arxiv.org/abs/2407.05237
Vehicle platoon often face the problem of lack of scalability of maneuvers in practical applications. Once a new scenario is added, the original program may no longer be available. To deal with this problem, this paper introduces a two-dimensional ma
Externí odkaz:
http://arxiv.org/abs/2207.01167
Publikováno v:
Xibei zhiwu xuebao, Vol 44, Iss 2, Pp 229-235 (2024)
Abstract [Objective] The transcription factor ERF has various biological functions, and plays important roles in regulating plant growth, development and responding to stress. Previous studies have shown that SmERF1 from Salvia miltiorrhiza was inv
Externí odkaz:
https://doaj.org/article/dd2129b850ae4ee2a12df13e701150b9
Autor:
Kong, Weiwei
This paper develops and analyzes an accelerated proximal descent method for finding stationary points of nonconvex composite optimization problems. The objective function is of the form $f+h$ where $h$ is a proper closed convex function, $f$ is a dif
Externí odkaz:
http://arxiv.org/abs/2205.13055
Autor:
Kong, Weiwei, Monteiro, Renato D. C.
This paper proposes and analyzes a dampened proximal alternating direction method of multipliers (DP.ADMM) for solving linearly-constrained nonconvex optimization problems where the smooth part of the objective function is nonseparable. Each iteratio
Externí odkaz:
http://arxiv.org/abs/2110.12502
Autor:
Kong, Weiwei, Monteiro, Renato D. C.
This paper proposes and analyzes an accelerated inexact dampened augmented Lagrangian (AIDAL) method for solving linearly-constrained nonconvex composite optimization problems. Each iteration of the AIDAL method consists of: (i) inexactly solving a d
Externí odkaz:
http://arxiv.org/abs/2110.11151
The purpose of this technical report is to review the main properties of an accelerated composite gradient (ACG) method commonly referred to as the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA). In addition, we state a version of FISTA for
Externí odkaz:
http://arxiv.org/abs/2107.01267
Publikováno v:
In Polymer 3 June 2024 304
Autor:
Kong, Weiwei, Wu, Xiaoying, Shen, Zhuowei, Wang, Meifang, Liu, Xinyu, Lin, Xiaoli, Qiu, Yingyin, Jiang, Hong, Chen, Jianghua, Lou, Yan, Huang, Hongfeng
Publikováno v:
In Kidney International Reports June 2024 9(6):1705-1717