no code implementations • 31 Jan 2025 • Yuchen Hu, Xi Chen, Weidong Liu, Xiaojun Mao
Distributed stochastic optimization algorithms can handle large-scale data simultaneously and accelerate model training.
no code implementations • 23 Apr 2024 • Rick Du, Huilong An, Keyu Wang, Weidong Liu
Ontologies provide formal representation of knowledge shared within Semantic Web applications.
1 code implementation • 22 Apr 2024 • Xiaofei Zhu, Liang Li, Weidong Liu, Xin Luo
To the end, in this paper, we propose a novel model named Multi-level Sequence Denoising with Cross-signal Contrastive Learning (MSDCCL) for sequential recommendation.
1 code implementation • 17 Feb 2024 • Yuzhuang Xu, Xu Han, Zonghan Yang, Shuo Wang, Qingfu Zhu, Zhiyuan Liu, Weidong Liu, Wanxiang Che
Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs.
no code implementations • 2 Jan 2024 • Weidong Liu, Xiaojun Mao, Xiaofei Zhang, Xin Zhang
To fast solve the non-smooth loss under a given privacy budget, we develop a Fast Robust And Privacy-Preserving Estimation (FRAPPE) algorithm for least absolute deviation regression.
no code implementations • 12 Dec 2023 • Kongming Liang, Xinran Wang, Rui Wang, Donghui Gao, Ling Jin, Weidong Liu, Xiatian Zhu, Zhanyu Ma, Jun Guo
Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization.
no code implementations • 4 Oct 2023 • Weidong Liu, Jiyuan Tu, Yichen Zhang, Xi Chen
In this paper, we develop an online robust policy evaluation procedure, and establish the limiting distribution of our estimator, based on its Bahadur representation.
1 code implementation • 9 Sep 2023 • Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, Yang Liu
Communication games, which we refer to as incomplete information games that heavily depend on natural language communication, hold significant research value in fields such as economics, social science, and artificial intelligence.
1 code implementation • 12 Jul 2023 • Yuzhuang Xu, Shuo Wang, Peng Li, Xuebo Liu, Xiaolong Wang, Weidong Liu, Yang Liu
Although neural machine translation (NMT) models perform well in the general domain, it remains rather challenging to control their generation behavior to satisfy the requirement of different users.
no code implementations • 17 Jun 2023 • Jiyuan Tu, Weidong Liu, Xiaojun Mao, Mingyue Xu
The debiased estimator is a crucial tool in statistical inference for high-dimensional model parameters.
no code implementations • 28 May 2023 • Kejie Tang, Weidong Liu, Yichen Zhang, Xi Chen
Stochastic gradient descent with momentum (SGDM) has been widely used in many machine learning and statistical applications.
1 code implementation • 13 Mar 2023 • Jiahao Xie, Wei Xu, Dingkang Liang, Zhanyu Ma, Kongming Liang, Weidong Liu, Rui Wang, Ling Jin
As the proposed method requires SR labels, we further propose a Super-Resolution Crowd Counting dataset (SR-Crowd).
no code implementations • 15 Oct 2022 • Xi Chen, Wenbo Jing, Weidong Liu, Yichen Zhang
The development of modern technology has enabled data collection of unprecedented size, which poses new challenges to many statistical estimation and inference problems.
no code implementations • 8 Sep 2022 • Weidong Liu, Jiyuan Tu, Xiaojun Mao, Xi Chen
Privacy-preserving data analysis has become more prevalent in recent years.
no code implementations • 11 Feb 2022 • Weidong Liu, Xiaojun Mao, Xin Zhang
Decentralized sparsity learning has attracted a significant amount of attention recently due to its rapidly growing applications.
no code implementations • 26 Oct 2021 • Yichen Zhou, Weidong Liu, Jing Ma, Xinghao Zhen, Yonggang Li
Further, to mitigate the impact of MMA, a defense strategy based on multi-index information active disturbance rejection control is proposed to improve the stability and anti-disturbance ability of the power system, which considers the impact factors of both mode damping and disturbance compensation.
1 code implementation • 16 Jun 2021 • Wenqing Zheng, Jiyang Xie, Weidong Liu, Zhanyu Ma
For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution.
no code implementations • 4 Mar 2021 • Jiyuan Tu, Weidong Liu, Xiaojun Mao, Xi Chen
Based on the proposed VRMOM estimator, we develop a general distributed inference algorithm that is robust against Byzantine failures.
no code implementations • 1 Jan 2021 • Jiyuan Tu, Weidong Liu, Xiaojun Mao
Privacy-preserving data analysis becomes prevailing in recent years.
1 code implementation • 4 Jul 2020 • Lixin Zou, Long Xia, Yulong Gu, Xiangyu Zhao, Weidong Liu, Jimmy Xiangji Huang, Dawei Yin
Therefore, the proposed exploration policy, to balance between learning the user profile and making accurate recommendations, can be directly optimized by maximizing users' long-term satisfaction with reinforcement learning.
no code implementations • ICML 2020 • Weidong Liu, Xiaojun Mao, Raymond K. W. Wong
In this paper, we consider matrix completion with absolute deviation loss and obtain an estimator of the median matrix.
no code implementations • 13 Jun 2019 • Xi Chen, Weidong Liu, Xiaojun Mao, Zhuoyi Yang
This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise.
no code implementations • 13 Feb 2019 • Lixin Zou, Long Xia, Zhuoye Ding, Jiaxing Song, Weidong Liu, Dawei Yin
Though reinforcement learning~(RL) naturally fits the problem of maximizing the long term rewards, applying RL to optimize long-term user engagement is still facing challenges: user behaviors are versatile and difficult to model, which typically consists of both instant feedback~(e. g. clicks, ordering) and delayed feedback~(e. g. dwell time, revisit); in addition, performing effective off-policy learning is still immature, especially when combining bootstrapping and function approximation.
1 code implementation • CVPR 2019 • Yuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu, Jun Wang
Neural style transfer has drawn considerable attention from both academic and industrial field.
no code implementations • 29 Nov 2018 • Xiaozhou Wang, Zhuoyi Yang, Xi Chen, Weidong Liu
In this paper, we propose a multi-round distributed linear-type (MDL) estimator for conducting inference for linear SVM.
no code implementations • 28 Nov 2018 • Xi Chen, Weidong Liu, Yichen Zhang
The key component in our method is the proposal of a computationally efficient estimator of $\Sigma^{-1} w$, where $\Sigma$ is the population Hessian matrix and $w$ is any given vector.
no code implementations • 18 Oct 2018 • Xi Chen, Weidong Liu, Yichen Zhang
This paper proposes a computationally efficient method, which only requires an initial QR estimator on a small batch of data and then successively refines the estimator via multiple rounds of aggregations.
no code implementations • 17 Mar 2012 • Weidong Liu, Xi Luo
We analyze an adaptive procedure based on cross validation, and establish its convergence rate under the Frobenius norm.