v201: Proceedings of ALT 2023

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

Summary

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 Shipra Agrawal and Francesco Orabona. The contributions span fundamental aspects of algorithmic learning, including advancements in online learning, reinforcement learning, and multi-armed bandit problems. Key topics explored involve robust learning under adversarial conditions, empirical risk minimization, and the computational complexity of various learning tasks. Additionally, papers address areas such as statistical estimation, differential privacy, graph learning, and the theoretical underpinnings of optimization algorithms, showcasing the breadth of current research in the field.

Key takeaway

The 34th International Conference on Algorithmic Learning Theory (ALT 2023) compiles foundational research advancing machine learning theory and algorithms. Key contributions address challenges in Reinforcement Learning (e.g., variance-reduced policy iteration, stochastic shortest path), Multi-Armed Bandits (best-arm identification, fixed budget), Online Learning, Robustness, and Differential Privacy. This collection offers critical theoretical insights and novel algorithmic solutions for researchers and practitioners in AI, statistics, and theoretical computer science.

Topics

• Algorithmic Learning Theory
• Online Learning
• Reinforcement Learning
• Multi-Armed Bandits
• Adversarial Robustness

Best for: Research Scientist, AI Scientist

Related on AIssential

• v237: Proceedings of ALT 2024 — 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 algo…
• 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.
• Best of both worlds: Stochastic & adversarial best-arm identification — Designing a single optimal learner for both stochastic and adversarial bandit best-arm identification is generally impossible.
• 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.
• Best of both worlds: Stochastic & adversarial best-arm identification — Optimal best-arm identification across both stochastic and adversarial bandit rewards is generally impossible.

Open in AIssential →

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