128 citations · 505 across the 21 of their papers we have counts for
21 papers
A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
Songtao Lu
Nonconvex constrained optimization problems can be used to model a number of machine learning problems, such as multi-class Neyman-Pearson classification and constrained Markov dec…
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Chia-Yu Chen, Jiamin Ni, Songtao Lu +8
Large-scale distributed training of Deep Neural Networks (DNNs) on state-of-the-art platforms is expected to be severely communication constrained. To overcome this limitation, num…
Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization
Zichong Li, Pin-Yu Chen, Sijia Liu +2
First-order methods have been studied for nonlinear constrained optimization within the framework of the augmented Lagrangian method (ALM) or penalty method. We propose an improved…
Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Tianxiang Gao, Songtao Lu, Jia Liu +1
We propose a new \textit{randomized Bregman (block) coordinate descent} (RBCD) method for minimizing a composite problem, where the objective function could be either convex or non…
Distributed Learning in the Non-Convex World: From Batch to Streaming Data, and Beyond
Tsung-Hui Chang, Mingyi Hong, Hoi-To Wai +2
Distributed learning has become a critical enabler of the massively connected world envisioned by many. This article discusses four key elements of scalable distributed processing…
Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
Tianxiang Gao, Songtao Lu, Jia Liu +1
In the applications of signal processing and data analytics, there is a wide class of non-convex problems whose objective function is freed from the common global Lipschitz continu…
Learn Electronic Health Records by Fully Decentralized Federated Learning
Songtao Lu, Yawen Zhang, Yunlong Wang +1
Federated learning opens a number of research opportunities due to its high communication efficiency in distributed training problems within a star network. In this paper, we focus…
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: A Joint Gradient Estimation and Tracking Approach
Haoran Sun, Songtao Lu, Mingyi Hong
Many modern large-scale machine learning problems benefit from decentralized and stochastic optimization. Recent works have shown that utilizing both decentralized computing and lo…
No-regret Non-convex Online Meta-Learning
Zhenxun Zhuang, Yunlong Wang, Kezi Yu +1
The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from past ta…
Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
Sijia Liu, Songtao Lu, Xiangyi Chen +5
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective fun…
SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
Songtao Lu, Meisam Razaviyayn, Bo Yang +2
This paper proposes low-complexity algorithms for finding approximate second-order stationary points (SOSPs) of problems with smooth non-convex objective and linear constraints. Wh…
Signal Demodulation with Machine Learning Methods for Physical Layer Visible Light Communications: Prototype Platform, Open Dataset and Algorithms
Shuai Ma, Jiahui Dai, Songtao Lu +4
In this paper, we investigate the design and implementation of machine learning (ML) based demodulation methods in the physical layer of visible light communication (VLC) systems.…
Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics
Hongmei Wang, Zhenzhen Wu, Shuai Ma +4
In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication syste…
Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
Songtao Lu, Ioannis Tsaknakis, Mingyi Hong +1
The min-max problem, also known as the saddle point problem, is a class of optimization problems which minimizes and maximizes two subsets of variables simultaneously. This class o…
Power Market Price Forecasting via Deep Learning
Yongli Zhu, Songtao Lu, Renchang Dai +2
A study on power market price forecasting by deep learning is presented. As one of the most successful deep learning frameworks, the LSTM (Long short-term memory) neural network is…
On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions
Songtao Lu, Mingyi Hong, Zhengdao Wang
The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc…
A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization: Convergence Analysis and Optimality
Songtao Lu, Mingyi Hong, Zhengdao Wang
Symmetric nonnegative matrix factorization (SymNMF) has important applications in data analytics problems such as document clustering, community detection and image segmentation. I…
Inexact Block Coordinate Descent Methods For Symmetric Nonnegative Matrix Factorization
Qingjiang Shi, Haoran Sun, Songtao Lu +2
Symmetric nonnegative matrix factorization (SNMF) is equivalent to computing a symmetric nonnegative low rank approximation of a data similarity matrix. It inherits the good data i…
Achievable Rates and Training Optimization for Uplink Multiuser Massive MIMO Systems
Songtao Lu, Zhengdao Wang
We study the performance of uplink transmission in a large-scale (massive) MIMO system, where all the transmitters have single antennas and the base station has a large number of a…
Joint Optimization of Power Allocation and Training Duration for Uplink Multiuser MIMO Communications
Songtao Lu, Zhengdao Wang
In this paper, we consider a multiuser multiple-input multiple-output (MU-MIMO) communication system between a base station equipped with multiple antennas and multiple mobile user…
Amplitude Space Sharing among the Macro-Cell and Small-Cell Users
Yafei Tian, Songtao Lu, Chenyang Yang
The crushing demand for wireless data services will soon exceed the capability of the current homogeneous cellular architecture. An emerging solution is to overlay small-cell netwo…