arXiv Machine Learning July 31, 2026 By Pavel Novoa-Hern\'andez

Expected Survival-Time Bounds for Robust Optimization Over Time under Isotropic Gaussian Dynamics

Read the original on arXiv Machine Learning →

arXiv:2607. 27280v1 Announce Type: cross Abstract: Robust Optimization Over Time (ROOT) is a recent branch of evolutionary dynamic optimization that seeks solutions capable of remaining effective across multiple consecutive environments.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 27

General Value Functions for Remaining Useful Life and Failure-Mode Prediction

arXiv:2607. 22268v1 Announce Type: cross Abstract: Remaining useful life (RUL) prediction and failure-mode classification are central tasks in predictive maintenance.

By Hao Yan, Ali Sarabi, Qing Zou, Boyang Xu

arXiv Machine Learning

Jul 17

Data Driven Block Replacement Scheduling

arXiv:2607. 15229v1 Announce Type: new Abstract: We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$.

By Aniruddhan Ganesaraman, VIdyadhar Kulkarni

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 31

Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning

arXiv:2607. 27626v1 Announce Type: new Abstract: Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound.

By Wentao Zhang, Wentao Mo

reinforcement-learning safety

arXiv Machine Learning

Jul 28

Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems

arXiv:2607. 23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation.

By Tanmay Khandait, Preetom Biswas, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Giulia Pedrielli

agents diffusion benchmarks safety

arXiv Machine Learning

Jul 28

Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories

arXiv:2607. 23454v1 Announce Type: new Abstract: Data-driven remaining useful life (RUL) prediction requires complete degradation trajectories for training, yet such run-to-failure data are scarce and expensive.

By Huy Hoang Le, Kim-Anh Nguyen

benchmarks safety data-engineering

arXiv AI

Aug 7

Posture and Sustainment Optimization Under Adversarial Uncertainty

arXiv:2608. 05256v1 Announce Type: new Abstract: Pre-commitment posture, the assignment of military assets to theater locations before conflict scenarios resolve, is a critical and formally unsolved problem in joint operational planning.

By Amelie Norris, Alyssa Lee, Natan Vidra, Spurthi Setty

reinforcement-learning safety

Related stories

General Value Functions for Remaining Useful Life and Failure-Mode Prediction

Data Driven Block Replacement Scheduling

Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning

Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems

Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories

Posture and Sustainment Optimization Under Adversarial Uncertainty