2 code implementations • ICLR 2020 • Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang
In this paper, we analyze the convergence of \texttt{FedAvg} on non-iid data and establish a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs.
2 code implementations • 9 Jun 2023 • Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Yixin Zhu, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Weijie Wu, Qianyu He, Rui Xu, Wenhao Huang, Jingping Liu, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, Yanghua Xiao
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs).
1 code implementation • 24 May 2023 • Dongjie Yang, Ruifeng Yuan, Yuantao Fan, Yifei Yang, Zili Wang, Shusen Wang, Hai Zhao
Therefore, we propose a method called RefGPT to generate enormous truthful and customized dialogues without worrying about factual errors caused by the model hallucination.
1 code implementation • 6 Apr 2022 • Hao Jin, Yang Peng, Wenhao Yang, Shusen Wang, Zhihua Zhang
We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction.
1 code implementation • 28 May 2015 • Shusen Wang
In recent years, a bunch of randomized algorithms have been devised to make matrix computations more scalable.
1 code implementation • 6 Nov 2018 • Vipul Gupta, Shusen Wang, Thomas Courtade, Kannan Ramchandran
We propose OverSketch, an approximate algorithm for distributed matrix multiplication in serverless computing.
Distributed, Parallel, and Cluster Computing Information Theory Information Theory
1 code implementation • Findings (NAACL) 2022 • Shusen Wang, Bosen Zhang, Yajing Xu, Yanan Wu, Bo Xiao
Zero-shot relation extraction aims to identify novel relations which cannot be observed at the training stage.
1 code implementation • COLING 2022 • Bin Duan, Shusen Wang, Xingxian Liu, Yajing Xu
To mitigate the catastrophic forgetting issue, we design the consistency regularization loss to make better use of the pseudo-labels and jointly train the model with both unsupervised and supervised data.
1 code implementation • Findings (NAACL) 2022 • Shusen Wang, Bin Duan, Yanan Wu, Yajing Xu
In this paper, we propose a novel method based on Instance Ranking and Label Calibration strategies (IRLC) to learn discriminative representations for open relation extraction.
no code implementations • NeurIPS 2018 • Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney
For distributed computing environment, we consider the empirical risk minimization problem and propose a distributed and communication-efficient Newton-type optimization method.
no code implementations • ICML 2017 • Shusen Wang, Alex Gittens, Michael W. Mahoney
In particular, there is a bias-variance trade-off in sketched MRR that is not present in sketched LSR.
no code implementations • ICML 2018 • Miles E. Lopes, Shusen Wang, Michael W. Mahoney
As a more practical alternative, we propose a bootstrap method to compute a posteriori error estimates for randomized LS algorithms.
no code implementations • 11 Oct 2017 • Youzuo Lin, Shusen Wang, Jayaraman Thiagarajan, George Guthrie, David Coblentz
We employ a data reduction technique in combination with the conventional kernel ridge regression method to improve the computational efficiency and reduce memory usage.
no code implementations • 6 Aug 2017 • Miles E. Lopes, Shusen Wang, Michael W. Mahoney
In recent years, randomized methods for numerical linear algebra have received growing interest as a general approach to large-scale problems.
no code implementations • 9 Jun 2017 • Shusen Wang, Alex Gittens, Michael W. Mahoney
This work analyzes the application of this paradigm to kernel $k$-means clustering, and shows that applying the linear $k$-means clustering algorithm to $\frac{k}{\epsilon} (1 + o(1))$ features constructed using a so-called rank-restricted Nystr\"om approximation results in cluster assignments that satisfy a $1 + \epsilon$ approximation ratio in terms of the kernel $k$-means cost function, relative to the guarantee provided by the same algorithm without the use of the Nystr\"om method.
no code implementations • 29 Mar 2015 • Shusen Wang, Zhihua Zhang, Tong Zhang
The Nystr\"om method is a special instance of our fast model and is approximation to the prototype model.
no code implementations • 22 Jun 2014 • Shusen Wang, Luo Luo, Zhihua Zhang
In this paper we conduct in-depth studies of an SPSD matrix approximation model and establish strong relative-error bounds.
no code implementations • 26 Dec 2014 • Shusen Wang, Tong Zhang, Zhihua Zhang
Low-rank matrix completion is an important problem with extensive real-world applications.
no code implementations • 30 Mar 2014 • Shusen Wang
Given a data matrix $X \in R^{n\times d}$ and a response vector $y \in R^{n}$, suppose $n>d$, it costs $O(n d^2)$ time and $O(n d)$ space to solve the least squares regression (LSR) problem.
no code implementations • 1 Apr 2014 • Shusen Wang, Zhihua Zhang
Recently, a variant of the Nystr\"om method called the modified Nystr\"om method has demonstrated significant improvement over the standard Nystr\"om method in approximation accuracy, both theoretically and empirically.
no code implementations • 18 Mar 2013 • Shusen Wang, Zhihua Zhang
The CUR matrix decomposition and the Nystr\"{o}m approximation are two important low-rank matrix approximation techniques.
no code implementations • NeurIPS 2012 • Shusen Wang, Zhihua Zhang
The CUR matrix decomposition is an important extension of Nyström approximation to a general matrix.
no code implementations • 13 Feb 2019 • Xiang Li, Shusen Wang, Zhihua Zhang
Subsampled Newton methods approximate Hessian matrices through subsampling techniques, alleviating the cost of forming Hessian matrices but using sufficient curvature information.
no code implementations • 24 Sep 2019 • Shusen Wang
On the one hand, our theories are based on weak and valid assumptions.
no code implementations • 24 Sep 2019 • Mengjiao Zhang, Shusen Wang
Collaborative learning allows participants to jointly train a model without data sharing.
no code implementations • 21 Oct 2019 • Xiang Li, Wenhao Yang, Shusen Wang, Zhihua Zhang
Recently, the technique of local updates is a powerful tool in centralized settings to improve communication efficiency via periodical communication.
no code implementations • 21 Dec 2019 • Songgaojun Deng, Shusen Wang, Huzefa Rangwala, Lijing Wang, Yue Ning
Forecasting influenza-like illness (ILI) is of prime importance to epidemiologists and health-care providers.
no code implementations • 27 Dec 2019 • Haishan Ye, Shusen Wang, Zhihua Zhang, Tong Zhang
Fast matrix algorithms have become the fundamental tools of machine learning in big data era.
1 code implementation • 19 Feb 2020 • Xiang Li, Shusen Wang, Kun Chen, Zhihua Zhang
As a practical surrogate of OPT, sign-fixing, which uses a diagonal matrix with $\pm 1$ entries as weights, has better computation complexity and stability in experiments.
no code implementations • 1 Mar 2021 • Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, Zhihua Zhang
The low communication power and the possible privacy breaches of data make the computation of eigenspace challenging.
no code implementations • 4 Aug 2022 • Xuting Tang, Jia Xu, Shusen Wang
To tackle this problem, we propose a special network architecture with a few-shot learning algorithm that allows the number of agents to vary during centralized training.
no code implementations • 9 Feb 2023 • Ziang Yan, Shusen Wang, Guorui Zhou, Jingjian Lin, Peng Jiang
Recent advances in this field often address the budget allocation problem using a two-stage paradigm: the first stage estimates the individual-level treatment effects using causal inference algorithms, and the second stage invokes integer programming techniques to find the optimal budget allocation solution.
no code implementations • 21 Jul 2023 • Shusen Wang
Recommender system (RS) is an established technology with successful applications in social media, e-commerce, entertainment, and more.