New preprint frames Bayesian experimental design under misspecification as a max-min game
canaesseth · x · 2026-11-10
A new preprint, to be presented at NeurIPS 2026 in Paris this December, studies Bayesian experimental design under model misspecification. The authors frame it as a max-min game and derive a robust expected information gain measure based on Sibson's alpha-mutual information. A follow-up preprint is teased, proposing a risk-sensitive RL approach to amortizing robust sequential experimental design.
More from Research
- HALO: an MCP plugin that audits personal agents' self-improvement loops on an L0-L5 scale — liuziwei7 · 2026-11-10
- LMMS Lab unveils Action-Sensing-Memory framework for personal multimodal agents — liuziwei7 · 2026-11-10
- Training-Free Weight Editing at 3ms: Decision Model Distillation Matches LoRA — Nandakishor_ml · 2026-11-10
- Terence Tao says AI Navier–Stokes proof is correct but mathematicians 'learned almost nothing' — sudoraohacker · 2026-11-10
- Must-read papers of the week: VFlash, GR00T 2, agent guardrails, AI-scientist benchmarks — TheTuringPost · 2026-11-10
- Hugging Face open-sources 14.8B DNA model Carbon-X, second only to GPT-6.1 Sol on GenomeQA — LoubnaBenAllal1 · 2026-11-10