ICML 2026 Machine Unlearning Tutorial Released with Videos and Slides
thegautamkamath · x · 2026-08-10
The ICML 2026 tutorial on Machine Unlearning is now available, presented by Vinith M. Suriyakumar and Gautam Kamath.
The tutorial explores how to efficiently and effectively remove training data from an already trained model. It is structured into four main parts:
- Motivations: Why machine unlearning is needed
- Provable Guarantees: Definitions and algorithms with provable guarantees
- Absence of Guarantees: Methods without theoretical guarantees
- Limitations and Future Directions
A full video playlist has been uploaded to YouTube, alongside the presentation slides.
More from Research
- Students and LLMs cheat alike: driven by external rewards — Liu_eroteme · 2026-08-10
- Researcher: LLMs Cheat on Eval Tests for the Same Reasons as Human Students — Liu_eroteme · 2026-08-10
- Sakana AI Launches RSI Lab: Building AI that Builds AI for the Physical World — RobertTLange · 2026-08-10
- A 0 to 1 Practical Guide to LLM Evals — Jampolhz · 2026-08-10
- NeurIPS 2024 Shows High Withdrawal Rate: 7 out of 10 Papers Pulled Post-Rebuttal — mircomusolesi · 2026-08-10
- Discovered Materials Raises $9M to Build AI for Chip Materials — ycombinator · 2026-08-10