v224: Proceedings of AutoML 2023

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Automated Machine Learning · Depth: Expert, short

Summary

Volume 224 of the Proceedings of the Second International Conference on Automated Machine Learning (AutoML), held from 12-15 November 2023 at the Hasso Plattner Institute in Potsdam, Germany, compiles a diverse set of research papers. The contributions span various core AutoML areas, including advancements in hyperparameter optimization (HPO), Bayesian optimization, and neural architecture search (NAS). Specific topics addressed include post hoc ensembling, symbolic explanations for HPO, domain adaptation, and multi-objective evolutionary optimization. The volume also features new tools like "AutoGluon–TimeSeries" for probabilistic time series forecasting and "AlphaD3M" as an open-source AutoML library, alongside research into fairness in ML ensembles and cost-effective HPO for Large Language Models. These papers collectively highlight ongoing efforts to enhance the efficiency, interpretability, and applicability of automated machine learning techniques across different domains.

Key takeaway

Volume 224 of the International Conference on Automated Machine Learning (AutoML) presents key advancements in optimizing ML pipelines, addressing challenges from hyperparameter optimization to neural architecture search. Papers detail novel techniques including Bayesian Optimization variants, symbolic explanations for HPO, and resource-efficient strategies for large language models and time series forecasting. These insights offer ML professionals practical methods to enhance model efficiency, robustness, and fairness across diverse applications, including visual anomaly and weapon detection.

Topics

• Automated Machine Learning
• Hyperparameter Optimization
• Bayesian Optimization
• Neural Architecture Search
• Ensemble Methods

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

Related on AIssential

• v256: Proceedings of AutoML 2024 — Volume 256 compiles the proceedings of the Third International Conference on Automated Machine Learning (AutoML), held from 9-12 September 2024 at Sorbonne Université, Paris, France.
• v64: AutoML 2016 Workshop Proceedings — Volume 64 of the Proceedings of the Workshop on Automatic Machine Learning, held on June 24, 2016, in New York, USA, presents diverse research focused on automating various aspects of machine learning workflows.
• A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction — Reproducible, log-driven AutoML reveals healthcare risk prediction pipeline component importance and search space redundancy.
• Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data — Automating feature preprocessing for tabular data can be framed as HPO or NAS, with evolution-based algorithms performing best.
• PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts — PEML co-optimizes continuous prompts via neural architecture search and model weights via LoRA for efficient multi-task LLM fine-tuning.
• Simplifying Image Classification with Azure AutoML for Images: A Practical Guide — Azure AutoML for Images automates complex computer vision tasks, enabling rapid deployment of production-ready models.

Open in AIssential →

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