donetmsiteserversecuusda – Page 23 – Open Data News Wire

donetmsiteserversecuusda

A Decade of Open Science: Milestones in Achieving UNESCO’S Open Science Recommendations

A Decade of Open Science: Milestones in Achieving UNESCO’S Open Science Recommendations

Today, the first biological and biomedical “data” journal GigaScience celebrates its 10th year of being at the…

AI Researchers Tackle Longstanding ‘Data Heterogeneity’ Problem for Federated Learning

AI Researchers Tackle Longstanding ‘Data Heterogeneity’ Problem for Federated Learning

Researchers from North Carolina State University have developed a new approach to federated learning that…

Study Examines Data Transparency, Health Equity in U.S. COVID-19 Response

Study Examines Data Transparency, Health Equity in U.S. COVID-19 Response

State governments varied widely in mitigation measures to address the COVID-19 pandemic such as school…

A New Data-Driven Model Could Provide a Powerful Policy Planning Tool to Combat the Nation’s Opioid Crisis

A New Data-Driven Model Could Provide a Powerful Policy Planning Tool to Combat the Nation’s Opioid Crisis

A Mass General-led team of public health modelers and substance use experts has developed a…

Public Release of ORNL Global Population Distribution Data Aids Humanitarian Support

Public Release of ORNL Global Population Distribution Data Aids Humanitarian Support

It’s a simple premise: To truly improve the health, safety, and security of human beings,…

Amazon Web Services Joins Q-NEXT Quantum Center

Amazon Web Services Joins Q-NEXT Quantum Center

Leading technology company to contribute to quantum communication research at Argonne-led center. Amazon Web Services…

Machine learning happens a lot like erosion. Data is hurled at a mathematical model like grains of sand skittering across a rocky landscape. Some of those grains simply sail along with little or no impact. But some of them make their mark: testing, hardening, and ultimately reshaping the landscape according to inherent patterns and fluctuations that emerge over time. Effective? Yes. Efficient? Not so much. Rick Blum, the Robert W. Wieseman Professor of Electrical and Computer Engineering at Lehigh University, seeks to bring efficiency to distributed learning techniques emerging as crucial to modern artificial intelligence (AI) and machine learning (ML). In essence, his goal is to hurl far fewer grains of data without degrading the overall impact. In the paper “Distributed Learning With Sparsified Gradient Differences,” published in a special ML-focused issue of the IEEE Journal of Selected Topics in Signal Processing, Blum and collaborators propose the use of “Gradient Descent method with Sparsification and Error Correction,” or GD-SEC, to improve the communications efficiency of machine learning conducted in a “worker-server” wireless architecture. The issue was published May 17, 2022. “Problems in distributed optimization appear in various scenarios that typically rely on wireless communications,” he says. “Latency, scalability, and privacy are fundamental challenges.” “Various distributed optimization algorithms have been developed to solve this problem,” he continues,”and one primary method is to employ classical GD in a worker-server architecture. In this environment, the central server updates the model’s parameters after aggregating data received from all workers, and then broadcasts the updated parameters back to the workers. But the overall performance is limited by the fact that each worker must transmit all of its data all of the time. When training a deep neural network, this can be on the order of 200 MB from each worker device at each iteration. This communication step can easily become a significant bottleneck on overall performance, especially in federated learning and edge AI systems.” Through the use of GD-SEC, Blum explains, communication requirements are significantly reduced. The technique employs a data compression approach where each worker sets small magnitude gradient components to zero—the signal-processing equivalent of not sweating the small stuff. The worker then only transmits to the server the remaining non-zero components. In other words, meaningful, usable data are the only packets launched at the model. “Current methods create a situation where each worker has expensive computational cost; GD-SEC is relatively cheap where only one GD step is needed at each round,” says Blum. Professor Blum’s collaborators on this project include his former student Yicheng Chen ’19G ’21PhD, now a software engineer with LinkedIn; Martin Takáč, an associate professor at the Mohamed bin Zayed University of Artificial Intelligence; and Brian M. Sadler, a Life Fellow of the IEEE, U.S. Army Senior Scientist for Intelligent Systems, and Fellow of the Army Research Laboratory.

Accelerating the Pace of Machine Learning

Machine learning happens a lot like erosion. Data is hurled at a mathematical model like…

CAS(ME)3: Next-Generation Micro-Expression Database with Depth Information and High Ecological Validity

CAS(ME)3: Next-Generation Micro-Expression Database with Depth Information and High Ecological Validity

Chinese researchers have established CAS(ME)3, a large-scale, spontaneous micro-expression database with depth information and high…

Online Data Could Be Used Against People Seeking Abortions If Roe V. Wade Falls

Online Data Could Be Used Against People Seeking Abortions If Roe V. Wade Falls

When the draft of a Supreme Court decision that would overturn Roe v. Wade was…

56% of Young People Are Concerned About Personal Data Security

56% of Young People Are Concerned About Personal Data Security

Sociologists at the Ural Federal University (UrFU) have identified digital fears among young people. According…

Older Posts Newer Posts