20 citations · 37 across the 9 of their papers we have counts for
10 papers
Partition-Aware Scheduling for Mobile Heterogeneous Inference Co-Execution
Zhuojin Li, Marco Paolieri, Leana Golubchik
Modern mobile inference runs on heterogeneous platforms combining mobile GPUs with multiple CPU core clusters. Existing optimizations typically exploit either inter-operator parall…
Efficient Algorithms for Interdicting Facilities in Trees and Bounded Treewidth Graphs
Ali Abbasi, Eli Friedman, Leana Golubchik +2
Given a graph of nodes partitioned into facilities and customers, the -edge interdiction covering problem (REIC) is to remove up to edges so as to maximize the total…
A Study on Inference Latency for Vision Transformers on Mobile Devices
Zhuojin Li, Marco Paolieri, Leana Golubchik
Given the significant advances in machine learning techniques on mobile devices, particularly in the domain of computer vision, in this work we quantitatively study the performance…
Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
Zhuojin Li, Marco Paolieri, Leana Golubchik
Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the other hand, their unified memory archi…
Estimating Ground Reaction Forces from Inertial Sensors
Bowen Song, Marco Paolieri, Harper E. Stewart +4
Objective: Our aim is to determine if data collected with inertial measurement units (IMUs) during steady-state running could be used to estimate ground reaction forces (GRFs) and…
Inference Latency Prediction at the Edge
Zhuojin Li, Marco Paolieri, Leana Golubchik
With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to ident…
Scheduling to Optimize Sojourn Time of Successful Jobs
Yuan Yao, Marco Paolieri, Leana Golubchik
Deep neural networks training jobs and other iterative computations frequently include checkpoints where jobs can be canceled based on the current value of monitored metrics. While…
Backdoor Attacks on Federated Meta-Learning
Chien-Lun Chen, Leana Golubchik, Marco Paolieri
Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by…
Throughput Prediction of Asynchronous SGD in TensorFlow
Zhuojin Li, Wumo Yan, Marco Paolieri +1
Modern machine learning frameworks can train neural networks using multiple nodes in parallel, each computing parameter updates with stochastic gradient descent (SGD) and sharing t…
SC-Share: Performance Driven Resource Sharing Markets for the Small Cloud
Sung-Han Lin, Ranjan Pal, Marco Paolieri +1
Small-scale clouds (SCs) often suffer from resource under-provisioning during peak demand, leading to inability to satisfy service level agreements (SLAs) and consequent loss of cu…