AI & ML
Data-Driven Factored Abstractions of Stochastic Systems
arXiv cs.SY0 views
arXiv:2611.24663v1 Announce Type: new Abstract: Formal verification and correct-by-design policy synthesis for stochastic dynamical systems face significant scalability challenges due to the curse of dimensionality. These challenges are exacerbated when the system dynamics are unknown and abstractions must be constructed from data. This paper introduces a data-driven framework for constructing factored interval Markov decision process (fIMDP) abstractions from noisy transition observations. Assuming conditional independence of successor coordinates and known coordinate-wise Lipschitz bounds on the dynamics, the framework estimates marginal transition probabilities rather than joint probabilities, resulting in an exponential reduction in the number of probability entries to be estimated and stored. We establish finite-sample confidence guarantees that the abstraction captures the concrete transition probabilities uniformly over each abstract region, enabling certified lower bounds on satisfaction probabilities for $\omega$-regular specifications. Experiments on benchmark systems, including pendulum swing-up, unicycle control, and a four-dimensional planar robot model, demonstrate improvements in certified satisfaction probability lower bounds of up to 25 percentage points compared with a state-of-the-art flat IMDP abstraction method. Our framework required up to 23x less memory and was consistently faster in constructing the abstraction.
Source:https://arxiv.org/abs/2611.24663PreviousData-driven control of polynomial systems using implicit methodsNextCross-Vehicle Transferability of Lateral Velocity Estimation on Production Vehicles through Input Selection and Data Augmentation
Related posts

Same message, four fates: SQS, SNS, Kafka and Redis Pub/Sub when a worker crashes
0dev.to AWS
Linux reserva a LKML para patches sem lista especializada
0dev.to Linux
How to Enable zram on Linux (and Why Keeping Your Swap File Makes It Worse)
0dev.to Linux

Asian tech stocks plunge as Anthropic's record IPO fails to stem an AI sell-off; SoftBank falls ~15%, TSMC falls 5%+, and Samsung and SK Hynix fall 6%+ (William Sandlund/Financial Times)
0Techmeme

BrightAI, which uses AI to help industrial companies detect malfunctioning equipment, raised $97M led by Smith Point, bringing its total funding to $184M (Maria Deutscher/SiliconANGLE)
0Techmeme

Sources: Nscale must seek a US license to provide ByteDance remote access to Nvidia GPUs under new rules; ByteDance made up ~73% of Nscale's 2025 revenue (Bloomberg)
0Techmeme