Performance Improvement
Performance improvement in various machine learning applications is a central research theme, focusing on enhancing model accuracy, efficiency, and robustness. Current efforts explore diverse strategies, including novel loss functions (e.g., for imbalanced datasets), optimized architectures (like wavelet-based networks and attention mechanisms), and innovative training techniques such as federated learning and adversarial training with parameter efficiency. These advancements have significant implications across diverse fields, from medical image analysis and drug discovery to recommendation systems and natural language processing, ultimately leading to more accurate, efficient, and reliable AI systems.
Papers
Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUs
Rishabh Jain, Vivek M. Bhasi, Adwait Jog, Anand Sivasubramaniam, Mahmut T. Kandemir, Chita R. Das
Improving Performance of Commercially Available AI Products in a Multi-Agent Configuration
Cory Hymel, Sida Peng, Kevin Xu, Charath Ranganathan
Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency
Bhavna Gopal, Huanrui Yang, Jingyang Zhang, Mark Horton, Yiran Chen
Refining Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models
Yanbing Chen, Ruilin Wang, Zihao Yang, Lavender Yao Jiang, Eric Karl Oermann
Enhancing Performance and User Engagement in Everyday Stress Monitoring: A Context-Aware Active Reinforcement Learning Approach
Seyed Amir Hossein Aqajari, Ziyu Wang, Ali Tazarv, Sina Labbaf, Salar Jafarlou, Brenda Nguyen, Nikil Dutt, Marco Levorato, Amir M. Rahmani
ARCO:Adaptive Multi-Agent Reinforcement Learning-Based Hardware/Software Co-Optimization Compiler for Improved Performance in DNN Accelerator Design
Arya Fayyazi, Mehdi Kamal, Massoud Pedram