arXiv research

Develops probabilistic safety regions for scalable classifiers.

Proposes a recursive MPC scheme with probabilistic safety guarantees for uncertain dynamic systems.

Study probabilistic safety of BNNs under adversarial attacks.

A new error bound improves safety in Bayesian optimization.

The paper tackles MAP inference over non-convex constraints in safety-critical settings.

Proposes CPO framework for robust decision-making with explainable uncertainty regions.

Generative model improves safety in self-driving simulators and human motion generation.

New method provides scalable safety guarantees for RL agents.

Proposes a method to accelerate safe sequential learning using offline data.

Improves safety region certification for smoothed classifiers without changing smoothing scheme.

Develops a method to simulate rare dangerous events in autonomous systems.

In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of artificial intelligence, in particular machine learning, are statistical models. Safety …

Deep-PrAE improves rare-event simulation for black-box systems.

A-NeSI scales approximate inference for probabilistic neurosymbolic learning.

MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.

Proposes a method to apply conformal prediction to probabilistic time series forecasting models.

Bayesian method synthesizes barrier certificates for unknown systems with latent states.

Safe learning of stochastic dynamics with safety constraints.

New bounds for kernel regression under non-Gaussian noise.

CARL safely adapts RL agents for safety-critical tasks.

The paper tackles safe exploration in RL by a conservative safety critic.

Probabilistic atlases provide essential spatial contextual information for image interpretation, Bayesian modeling, and algorithmic processing. Such atlases are typically constructed by grouping subjects with similar demographic information. Importantly, use of the same scanner minimizes inter-group variability. Howeve…

Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.

Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to misclassify it. With potential applications including perception modules and end-t…

Meta-learning priors improves safe Bayesian optimization.

Extends neural net safety guarantees by proving structural properties.

Unified approach detects traffic conflicts across various interactions.

Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. E…

Safe RL in linear systems achieves $\sqrt{T}$-regret.

New bounds on trajectory safety in training models with Langevin Dynamics.

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide idealistic probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by separating the constraint functions from the principal objective to create a hiera…

Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable problem. While approximation methods exist, they do not come with guarantees, mak…

Paper defines ε-Safe Decision Regions for exponential family distributions and approximates them for unbalanced data.

Enforcing safety is a key aspect of many problems pertaining to sequential decision making under uncertainty, which require the decisions made at every step to be both informative of the optimal decision and also safe. For example, we value both efficacy and comfort in medical therapy, and efficiency and safety in robo…

Meta-active learning optimizes control of safety-critical systems by efficiently learning dynamics and configurations.

Combines Lyapunov functions with controller synthesis for safe control policies.

ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.

Safe RL with binary feedback using SABRE algorithm.

Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviours are unexplainable, and they cannot guarantee safety…

Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.

CSP improves time-series forecasting without training, outperforming DeepNPTS in speed and accuracy.

Probabilistic classifiers output a probability distribution on target classes rather than just a class prediction. Besides providing a clear separation of prediction and decision making, the main advantage of probabilistic models is their ability to represent uncertainty about predictions. In safety-critical applicatio…

We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However, enumerating these regions is prohibitive and the known analytical bounds are identical for…

This work establishes safe reinforcement learning for LQR with nonlinear baselines.

Study identifies regions where scoring rules reliably detect forecast errors.

Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics. Most semantic inpainting algorithms are deterministic: given an image with missing regions, a single inpainted image is generated. However, there are often several plausible inpaintings for a…

The paper provides tighter error bounds for GPR under bounded support noise.

In Bayesian classification, it is important to establish a probabilistic model for each class for likelihood estimation. Most of the previous methods modeled the probability distribution in the whole sample space. However, real-world problems are usually too complex to model in the whole sample space; some fundamental …