35 citations · 68 across the 22 of their papers we have counts for
22 papers
Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learning
Jie Peng, Weiyu Li, Stefan Vlaski +1
Robustness to malicious attacks is crucial for practical decentralized signal processing and machine learning systems. A typical example of such attacks is label poisoning, meaning…
Binary and Ternary Quantization Can Enhance Feature Discrimination
Weizhi Lu, Mingrui Chen, Weiyu Li
Quantization is widely applied in machine learning to reduce computational and storage costs for both data and models. Considering that classification tasks are fundamental to the…
Data-adaptive Safety Rules for Training Reward Models
Xiaomin Li, Mingye Gao, Zhiwei Zhang +2
Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models…
Mean Aggregator is More Robust than Robust Aggregators under Label Poisoning Attacks on Distributed Heterogeneous Data
Jie Peng, Weiyu Li, Stefan Vlaski +1
Robustness to malicious attacks is of paramount importance for distributed learning. Existing works usually consider the classical Byzantine attacks model, which assumes that some…
Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error
Jie Peng, Weiyu Li, Qing Ling
This paper studies Byzantine-robust stochastic optimization over a decentralized network, where every agent periodically communicates with its neighbors to exchange local models, a…
On the Relationship of Optimal State Feedback and Disturbance Response Controllers
Runyu Zhang, Yang Zheng, Weiyu Li +1
This paper studies the relationship between state feedback policies and disturbance response policies for the standard Linear Quadratic Regulator (LQR). For open-loop stable plants…
Source-Function Weighted-Transfer Learning for Nonparametric Regression with Seemingly Similar Sources
Lu Lin, Weiyu Li
The homogeneity, or more generally, the similarity between source domains and a target domain seems to be essential to a positive transfer learning. In practice, however, the simil…
Simultaneous Best Subset Selection and Dimension Reduction via Primal-Dual Iterations
Canhong Wen, Ruipeng Dong, Xueqin Wang +2
Sparse reduced rank regression is an essential statistical learning method. In the contemporary literature, estimation is typically formulated as a nonconvex optimization that ofte…
On the Optimal Control of Network LQR with Spatially-Exponential Decaying Structure
Runyu Zhang, Weiyu Li, Na Li
This paper studies network LQR problems with system matrices being spatially-exponential decaying (SED) between nodes in the network. The major objective is to study whether the op…
A Correlation-Ratio Transfer Learning and Variational Stein's Paradox
Lu Lin, Weiyu Li
A basic condition for efficient transfer learning is the similarity between a target model and source models. In practice, however, the similarity condition is difficult to meet or…
Ternary and Binary Quantization for Improved Classification
Weizhi Lu, Mingrui Chen, Kai Guo +1
Dimension reduction and data quantization are two important methods for reducing data complexity. In the paper, we study the methodology of first reducing data dimension by random…
Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning
Weizhi Lu, Mingrui Chen, Kai Guo +1
Recently, the method that learns networks layer by layer has attracted increasing interest for its ease of analysis. For the method, the main challenge lies in deriving an optimiza…
Deep Learning to Ternary Hash Codes by Continuation
Mingrui Chen, Weiyu Li, Weizhi Lu
Recently, it has been observed that {0,1,-1}-ternary codes which are simply generated from deep features by hard thresholding, tend to outperform {-1,1}-binary codes in image retri…
Online Updating Statistics for Heterogenous Updating Regressions via Homogenization Techniques
Lin Lu, Lu Jun, Li Weiyu
Under the environment of big data streams, it is a common situation where the variable set of a model may change according to the condition of data streams. In this paper, we propo…
Stochastic Alternating Direction Method of Multipliers for Byzantine-Robust Distributed Learning
Feng Lin, Weiyu Li, Qing Ling
This paper aims to solve a distributed learning problem under Byzantine attacks. In the underlying distributed system, a number of unknown but malicious workers (termed as Byzantin…
Unified Rules of Renewable Weighted Sums for Various Online Updating Estimations
Lu Lin, Weiyu Li, Jun Lu
This paper establishes unified frameworks of renewable weighted sums (RWS) for various online updating estimations in the models with streaming data sets. The newly defined RWS lay…
Best Subset Selection in Reduced Rank Regression
Canhong Wen, Weiyu Li, Junxian Zhu +1
We design a new algorithm on the best subset selection model in reduced rank regression.
Communication-Censored Linearized ADMM for Decentralized Consensus Optimization
Weiyu Li, Yaohua Liu, Zhi Tian +1
In this paper, we propose a communication- and computation-efficient algorithm to solve a convex consensus optimization problem defined over a decentralized network. A remarkable e…
Communication-Censored Distributed Stochastic Gradient Descent
Weiyu Li, Tianyi Chen, Liping Li +2
This paper develops a communication-efficient algorithm to solve the stochastic optimization problem defined over a distributed network, aiming at reducing the burdensome communica…
A semiparametric single-index estimator for a class of estimating equation models
Marian Hristache, Weiyu Li, Valentin Patilea
We propose a two-step pseudo-maximum likelihood procedure for semiparametric single-index regression models where the conditional variance is a known function of the regression and…
Sparse Matrix-based Random Projection for Classification
Weizhi Lu, Weiyu Li, Kidiyo Kpalma +1
As a typical dimensionality reduction technique, random projection can be simply implemented with linear projection, while maintaining the pairwise distances of high-dimensional da…
Near-optimal Binary Compressed Sensing Matrix
Weizhi Lu, Weiyu Li, Kidiyo Kpalma +1
Compressed sensing is a promising technique that attempts to faithfully recover sparse signal with as few linear and nonadaptive measurements as possible. Its performance is largel…