System Performance
System performance research focuses on optimizing the efficiency and accuracy of various computational systems, from machine learning models to robotic controllers and even quantum computers. Current research emphasizes improving model architectures (e.g., graph-oriented databases for language models, retention-based networks for multi-agent reinforcement learning) and training techniques (e.g., hard sample mining, co-optimization of design and control), while also addressing issues like fairness, robustness, and explainability. These advancements have significant implications for diverse fields, impacting the development of more efficient and reliable AI systems, improved medical diagnostics, and enhanced manufacturing processes.
Papers
A Meta-Learning Approach to Predicting Performance and Data Requirements
Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto
Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems
Pratinav Seth, Akshat Bhandari, Kumud Lakara
Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection
Zhen Cheng, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu
Using simulation to quantify the performance of automotive perception systems
Zhenyi Liu, Devesh Shah, Alireza Rahimpour, Devesh Upadhyay, Joyce Farrell, Brian A Wandell