arXiv research

The paper optimizes exceptions in a statistical production system using machine learning.

Fatal accidents are a major issue hindering the wide acceptance of safety-critical systems using machine-learning and deep-learning models, such as automated-driving vehicles. Quality assurance frameworks are required for such machine learning systems, but there are no widely accepted and established quality-assurance …

As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be able to trust the systems that are being designed. In this survey we present assura…

People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their actions, and to know how to use them appropriately. Many techniques have been devised …

GRAND ensures node-level differential privacy for network data.

Paper proposes a sequential statistical test for comparing imitation learning policies with near-optimal stopping.

A new process model for machine learning applications with quality assurance.

The paper designs neural networks with assurance for controlling nonlinear systems.

Machine learning has evolved into an enabling technology for a wide range of highly successful applications. The potential for this success to continue and accelerate has placed machine learning (ML) at the top of research, economic and political agendas. Such unprecedented interest is fuelled by a vision of ML applica…

In recent years, car makers and tech companies have been racing towards self driving cars. It seems that the main parameter in this race is who will have the first car on the road. The goal of this paper is to add to the equation two additional crucial parameters. The first is standardization of safety assurance --- wh…

We provide sufficient conditions assuring that a suitably decorated 2-polyhedron can be thickened to a compact 4-dimensional Stein domain. We also study a class of flat polyhedra in 4-manifolds and find conditions assuring that they admit Stein, compact neighborhoods. We base our calculations on Turaev's shadows suitab…

Advances in the field of Machine Learning and Deep Neural Networks (DNNs) has enabled rapid development of sophisticated and autonomous systems. However, the inherent complexity to rigorously assure the safe operation of such systems hinders their real-world adoption in safety-critical domains such as aerospace and med…

Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). However, they may introduce new types of hazards that can have disastrous consequences and need to be addressed for engineering trustworthy systems. Although deep neural networks offer advanced capabilities, t…

Develops ML-DQA for healthcare data quality assurance.

The study models life insurance policy cancellations using statistical and machine learning methods.

A novel ML verification technique using manifold learning.

New method improves local precipitation predictions using video diffusion.

Two novel models predict bus travel times with uncertainty, improving connection assurance.

Given a properly embedded graph Gamma in a ball B and a punctured sphere Sigma properly embedded in B - Gamma, we examine the conditions on Gamma that are necessary to assure that Sigma is boundary parallel.

We study the geometry of the leaf closure space of regular and singular Riemannian foliations. We give conditions which assure that this leaf space is a singular symplectic or Kähler space.

This study improves audit sampling by using sequential procedures with statistical guarantees.

New framework uses OR to ensure AI systems make safe decisions.

We present a simple remark that assures that the invariant theory of certain real Lie groups coincides with that of the underlying affine, real algebraic groups. In particular, this result applies to the non-compact orthogonal or symplectic Lie groups.

Framework ensures alignment between humans and machines in LLMs.

Let $(M,ω,J,g)$ be a non-compact almost Kähler manifold. In this paper we provide various criteria that assure that $ω^k$ induces a non trivial class in the reduced $L^p$ maximal/minimal cohomology of $(M,g)$. Furthermore in the last part we explore some topological applications of our results.

With the rapid growth of crowdsourcing platforms it has become easy and relatively inexpensive to collect a dataset labeled by multiple annotators in a short time. However due to the lack of control over the quality of the annotators, some abnormal annotators may be affected by position bias which can potentially degra…

This paper introduces modal epistemic tools for risk management.

Proposes real-time risk monitoring for machine learning systems under unknown shifts.

A new method enhances signal recovery with FDR control.

The paper finds sign-changing solutions for a specific type of elliptic equation.

RAGuard improves safety in LLMs for offshore wind maintenance.

Let $G$ be a compact connected Lie group and let H be a subgroup fixed by an involution. A classical result assures that the action of the complex reductive group $H_C$ on the flag variety $F$ of $G$ admits a finite number of orbits. In this article we propose a formula for the branching coefficients of the symmetric p…

We introduce a novel Deep Learning framework, which quantitatively estimates image segmentation quality without the need for human inspection or labeling. We refer to this method as a Quality Assurance Network -- QANet. Specifically, given an image and a `proposed' corresponding segmentation, obtained by any method inc…

This lecture is devoted to review some of the main properties of multisymplectic geometry. In particular, after reminding the standard definition of multisymplectic manifold, we introduce its characteristic submanifolds, the canonical models, and other relevant kinds of multisymplectic manifolds, such as those where th…

Stablecoins promise to bridge fiat currencies with the world of cryptocurrencies. They provide a way for users to take advantage of the benefits of digital currencies, such as ability to transfer assets over the internet, provide assurance on minting schedules and scarcity, and enable new asset classes, while also part…

A new framework uses deep reinforcement learning to improve aircraft separation in busy airspace.

SAFER improves personalized treatment recommendations for dynamic clinical contexts.

To improve the performance of Intensive Care Units (ICUs), the field of bio-statistics has developed scores which try to predict the likelihood of negative outcomes. These help evaluate the effectiveness of treatments and clinical practice, and also help to identify patients with unexpected outcomes. However, they have…

In this paper, we present the principal components of an economic scenario generator (ESG), both for the theoretical design and for practical implementation. The choice of these components should be linked to the ultimate vocation of the economic scenario generator, which can be either a tool for pricing financial prod…

Survey of AI-based outlier detection methods for various domains.

Existence of hypersurfaces in warped product manifolds proven.

Practitioners sometimes suggest to use a combination of Sobol sequences and orthonormal polynomials when applying an LSMC algorithm for evaluation of option prices or in the context of risk capital calculation under the Solvency II regime. In this paper, we give a theoretical justification why good implementations of a…

The article presents a general discrete time dividend valuation model when the dividend growth rate is a general continuous variable. The main assumption is that the dividend growth rate follows a discrete time semi-Markov chain with measurable space. The paper furnishes sufficient conditions that assure finiteness of …

For n >1, if the Seifert form of a knotted 2n-1 sphere K in S^{2n+1} has a metabolizer, then the knot is slice. Casson and Gordon proved that this is false in dimension three (n = 1). However, in the three dimensional case it is true that if the metabolizer has a basis represented by a strongly slice link then K is sli…

Enhances robustness for time series classification using self-ensemble method.

Method certifies edge predictions with cloud-level reliability.

Origami solves real cubic equations, revealing a specific curve.

Novel approach ensures stability of compact schemes for variable PDEs.