35 citations · 133 across the 19 of their papers we have counts for
10 papers · 1 filter
A global convergence theory for deep ReLU implicit networks via over-parameterization
Tianxiang Gao, Hailiang Liu, Jia Liu +2
Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectu…
Anarchic Federated Learning
Haibo Yang, Xin Zhang, Prashant Khanduri +1
Present-day federated learning (FL) systems deployed over edge networks consists of a large number of workers with high degrees of heterogeneity in data and/or computing capabiliti…
Toward Efficient Online Scheduling for Distributed Machine Learning Systems
Menglu Yu, Jia Liu, Chuan Wu +2
Recent years have witnessed a rapid growth of distributed machine learning (ML) frameworks, which exploit the massive parallelism of computing clusters to expedite ML training. How…
Federated Learning with Fair Worker Selection: A Multi-Round Submodular Maximization Approach
Fengjiao Li, Jia Liu, Bo Ji
In this paper, we study the problem of fair worker selection in Federated Learning systems, where fairness serves as an incentive mechanism that encourages more workers to particip…
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Prashant Khanduri, Pranay Sharma, Haibo Yang +4
Federated Learning (FL) refers to the paradigm where multiple worker nodes (WNs) build a joint model by using local data. Despite extensive research, for a generic non-convex FL pr…
CFedAvg: Achieving Efficient Communication and Fast Convergence in Non-IID Federated Learning
Haibo Yang, Jia Liu, Elizabeth S. Bentley
Federated learning (FL) is a prevailing distributed learning paradigm, where a large number of workers jointly learn a model without sharing their training data. However, high comm…
Incentivized Bandit Learning with Self-Reinforcing User Preferences
Tianchen Zhou, Jia Liu, Chaosheng Dong +1
In this paper, we investigate a new multi-armed bandit (MAB) online learning model that considers real-world phenomena in many recommender systems: (i) the learning agent cannot pu…
A Sum-of-Ratios Multi-Dimensional-Knapsack Decomposition for DNN Resource Scheduling
Menglu Yu, Chuan Wu, Bo Ji +1
In recent years, to sustain the resource-intensive computational needs for training deep neural networks (DNNs), it is widely accepted that exploiting the parallelism in large-scal…
GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning
Xin Zhang, Jia Liu, Zhengyuan Zhu +1
Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementat…
Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning
Haibo Yang, Minghong Fang, Jia Liu
Federated learning (FL) is a distributed machine learning architecture that leverages a large number of workers to jointly learn a model with decentralized data. FL has received in…