Brief

last 24h

[2/2] 221 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

TOOL · arXiv stat.ML English(EN) · 4d

A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems

Researchers have developed a new PAC-Bayes framework designed to learn controllers for unknown stochastic linear discrete-time systems. This framework provides a data-dependent, high-probability bound on the performance of any learned controller. The proposed algorithms offer theoretical guarantees and are applicable to both finite and infinite controller spaces, with numerical results indicating performance comparable to LQG in specific scenarios. AI

IMPACT Introduces a novel theoretical framework for control systems, potentially impacting AI applications in robotics and automation.
- PAC-Bayes
- Yujia Luo
RESEARCH · arXiv stat.ML English(EN) · 5d · [2 sources]

MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

Researchers have developed a PAC-Bayesian framework to quantify epistemic uncertainty in test-time adaptation (TTA) methods. This framework uses maximum mean discrepancy (MMD) between source and target distributions to derive generalization bounds. By interpreting MMD-balls as credal sets, the approach separates epistemic from aleatoric uncertainty, offering a principled way to decide when adaptation is beneficial. AI

IMPACT Provides a theoretical foundation for understanding and quantifying uncertainty in models adapting to new data distributions.