v157: Proceedings of ACML 2021

· Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Data Science & Analytics · Depth: Expert, long

Summary

This volume presents the proceedings of The 13th Asian Conference on Machine Learning (ACML), which took place virtually from November 17-19, 2021, featuring a diverse collection of contributed research papers. The papers cover a broad spectrum of advanced machine learning topics, including novel optimization algorithms like Riemannian LBFGS and accelerated nonconvex optimization, alongside significant advancements in deep reinforcement learning, such as improved actor-critic methods and multi-agent coordination. Contributions also span neural network architectures, encompassing graph neural networks, model compression, quantization, and neural architecture search. Furthermore, the proceedings address critical practical challenges, including data imbalance, fairness in classification, adversarial robustness, and various applications in computer vision, natural language processing, and recommendation systems.

Key takeaway

The 13th Asian Conference on Machine Learning (ACML 2021) presents over 90 papers advancing core ML algorithms and diverse applications. Key contributions include novel optimization methods like Vector Transport Free Riemannian LBFGS, robust deep learning architectures such as Quaternion Graph Neural Networks, and practical solutions for challenges like imbalanced data (ExNN-SMOTE) and adversarial attacks. This volume offers valuable insights for researchers and practitioners aiming to enhance model efficiency, robustness, and fairness across domains from computer vision to reinforcement learning and data synthesis.

Topics

Code references

Best for: AI Scientist, Research Scientist, Machine Learning Engineer

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.