ICML 2026 Tutorial: Optimization for Neural Network Training
udmrzn · x · 2026-07-08
At the ICML 2026 conference, Professor Mark Schmidt delivered a tutorial on "Optimization for Neural Network Training," with lecture notes now publicly available. The content focuses on optimization methods in deep learning training, making it ideal for researchers and engineers looking to systematically understand the underlying math and methodologies.
Related event: ICML 2026 Neural Network Optimization Tutorial Reshapes Intuitions(3 posts)→
More from Research
- Deep Learning Course Adds Mechanistic Interpretability Lecture This Winter — CSProfKGD · 2026-10-26
- INCLUDE-2.0 benchmark evaluates regional knowledge across 91 languages and 86 countries — ABosselut · 2026-10-26
- CoRL paper: flow-matching VLAs can run 1-step Euler inference with no retraining — kaixhin · 2026-10-26
- CoVer at EMNLP 2026: Training Code LLMs to Generate and Self-Verify Simultaneously — algo_diver · 2026-10-26
- Robotic dexterity should be judged on speed, force control and tool use, not copying humans — DJiafei · 2026-10-26
- Turing-complete malware can run in PyTorch's backward pass via a zero-valued loss — retr0jirachi · 2026-10-26