v237: Proceedings of ALT 2024

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Mathematics & Computational Sciences · Depth: Expert, medium

Summary

The 35th International Conference on Algorithmic Learning Theory (ALT 2024), held February 25-28, 2024, in La Jolla, California, USA, showcased significant advancements across the theoretical and algorithmic aspects of machine learning. Research presented included novel approaches to sample-efficient in-context learning for sparse retrieval and deep dives into the learnability and privacy guarantees of various models, such as Mixtures of Gaussians and PAC learning. A substantial portion of the proceedings focused on bandit algorithms, exploring regret bounds, adversarial settings, and collaborative learning, alongside contributions to online learning, reinforcement learning, and optimization theory. Other notable topics encompassed semi-supervised learning, neural network theory, the computational benefits of multimodal learning, and the theoretical limits of boosting and sample compression.

Key takeaway

The 35th International Conference on Algorithmic Learning Theory (ALT 2024) proceedings, Volume 237, features foundational research addressing critical challenges in machine learning, including privacy, robustness, and sample efficiency. Papers delve into topics such as differentially private learnability, optimal regret bounds for adversarial bandits, and the sample complexity of deep neural networks. This collection provides essential theoretical insights for researchers and developers building secure, efficient, and reliable AI systems.

Topics

• Differential Privacy
• Bandit Algorithms
• Online Learning
• Reinforcement Learning
• Neural Network Theory

Best for: Research Scientist, AI Scientist, AI Student

Related on AIssential

• v201: Proceedings of ALT 2023 — Volume 201 presents the proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), held in Singapore, featuring a diverse collection of research papers edited by Shipr…
• v132: ALT 2021 Proceedings — Volume 132 compiles the proceedings of the 32nd International Conference on Algorithmic Learning Theory (ALT 2021), a virtual event held from March 16-19, 2021, edited by Vitaly Feldman, Katrina Ligett, and Sivan Sabato.
• The Sample Complexity of Multiclass and Sparse Contextual Bandits — Algorithms achieve optimal sample complexity for s-sparse contextual bandits, closing a significant gap in prior work.

Open in AIssential →

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