Survey of algorithmic assurances for trust in AI agents.
problem Ensuring trust in AI agents designed for human-autonomy relationships.
method Formal definition and classification of algorithmic assurances, synthesis of research across AI communities.
result Algorithmic assurances fall along a spectrum impacting agent core functionality.
Survey of assurances for trust in human-autonomy systems.
problem Ensuring trust in human-autonomy systems.
method Survey and review of existing research.
result Refined definition of assurances for trust.
Identifies open problems in quality assurance of safety-critical ML systems.
problem Quality assurance for safety-critical ML systems, especially in automated driving.
method Identified and classified open problems using automated-driving vehicles as an example.
result Open problems require interdisciplinary knowledge from various fields.
Survey of methods for ML assurance across its lifecycle stages.
problem Ensuring safety of ML in safety-critical applications.
method Comprehensive survey of methods at each ML lifecycle stage.
result Identification of open challenges in ML assurance.
Quantifier elimination enhances safety assurance of deep neural networks.
problem Rigorously assure safe operation of sophisticated, autonomous systems like DNNs.
method Use quantifier elimination as a formal method to enhance safety assurance.
result Initial results show QE can precisely analyze robustness of DNNs.
Develops ML-DQA for healthcare data quality assurance.
problem Inconsistent use of real-world data in machine learning projects.
method Develops ML-DQA framework based on RWD best practices.
result Five generalizable practices emerge from ML-DQA implementation.
The paper optimizes exceptions in a statistical production system using machine learning.
problem Lack of curated and labeled training data for machine learning in data quality assurance.
method Explainable supervised machine learning to identify and prioritize exceptions.
result Improvement in the quality and efficiency of exceptions generated and authenticated by users.
A new process model for machine learning applications with quality assurance.
problem Lack of standard process model for machine learning applications.
method Six-phase process model with quality assurance methodology.
result Proposes a new process model for machine learning applications.
Proposes a mathematical model for safe and scalable self-driving cars.
problem Ensuring safety and scalability in self-driving cars.
method Introduces Responsibility-Sensitive Safety (RSS) model and scalable design.
result Proposes a mathematical model for safety assurance and scalable design.
The paper designs neural networks with assurance for controlling nonlinear systems.
problem Designing neural networks with assurance for nonlinear system control.
method Bounding the number of affine functions needed for a CPWA function, connecting it to a TLL NN architecture.
result The TLL NN architecture is parameterized by the number of affine functions in the CPWA function it realizes.
The paper uses conformal prediction to monitor CPS with machine learning components.
problem Ensuring trustworthy CPS with machine learning components.
method Conformal prediction framework for real-time assurance monitoring of CPS with machine learning.
result The method provides well-calibrated confidence and limits the number of alarms.
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…
A novel ML verification technique using manifold learning.
problem Ensuring trust in machine learning systems.
method Variational autoencoder for extracting a low-dimensional manifold from high-dimensional training data.
result The manifold provides diverse test data, fault-revealing test cases, and independent runtime trust assessment.
Two novel models predict bus travel times with uncertainty, improving connection assurance.
problem Improving bus connection assurance by handling travel time uncertainty.
method Two novel approaches: Deep Quantile Regression (DQR) and Bayesian Recurrent Neural Networks (BRNN).
result DQR model performs best for 80%, 90%, and 95% prediction intervals, with small underestimation.
QANet estimates image segmentation quality without human inspection.
problem Quantitative evaluation of image segmentation quality.
method QANet is a Quality Assurance Network that solves a regression problem to estimate quality measures.
result QANet accurately estimates segmentation quality with respect to ground truth.
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.
New framework uses OR to ensure AI systems make safe decisions.
problem Ensuring generative AI systems make safe decisions as they gain autonomy.
method Developed a conceptual framework combining flow-based models and adversarial robustness.
result Increased autonomy requires new OR approaches for feasibility, robustness, and stress testing.
The paper explains why combining Sobol sequences and polynomials improves LSMC stability.
problem Improving numerical stability in LSMC algorithms.
method Theoretical justification and derivation of a bound for numerical stability.
result Explicit bound for the number of outer scenarios for numerical stability.
GRAND ensures node-level differential privacy for network data.
problem Lack of node-level differential privacy for network data.
method Proposes GRAND, the first mechanism for releasing networks with node-level differential privacy and preserving structural properties.
result GRAND releases networks while ensuring node-level differential privacy and preserving structural properties.
In life sciences, the experts generally use empirical knowledge to recode variables, choose interactions and perform selection by classical approach. The aim of this work is to perform automatic learning algorithm for variables selection which can lead to know if experts can be help in they decision or simply replaced …
Origami solves real cubic equations, revealing a specific curve.
problem Solving real cubic equations using origami.
method Investigating a specific real cubic curve F(x,y)=0 and analyzing its properties. result The shape of Beloch's curve is determined by the Hessian at its singular point.
This paper introduces modal epistemic tools for risk management.
problem Identifying and certifying risk claims when institutions lack the necessary epistemic stance.
method Develops crisp and fuzzy modal semantics for assurance and working commitment, distinguishing between object-level risk claims and meta-level epistemic diagnostics.
result Risk governance should model evidential incompleteness and failures of escalation, not just hazards and losses.
Real Lie groups' invariant theory matches that of their affine counterparts.
problem Matching invariant theory of real Lie groups with affine groups.
method Simple remark showing coincidence.
result Invariant theory of real Lie groups equals that of their affine counterparts.
The paper finds sign-changing solutions for a specific type of elliptic equation.
problem Existence of sign-changing solutions for a Yamabe type equation.
method Investigates a critical elliptic equation with a Yamabe type operator on a compact manifold with boundary.
result Existence of sign-changing solutions assured under certain geometric conditions.
RAGuard improves safety in LLMs for offshore wind maintenance.
problem Conventional LLMs fail with specialised or unexpected scenarios in offshore wind maintenance.
method Integrates safety-critical documents alongside technical manuals in RAG framework.
result RAGuard increases safety recall from almost 0% to over 50% while maintaining technical recall above 60%.
modAL simplifies active learning in Python.
problem Making active learning research and practice easier.
method Clear, modular design; compatibility with scikit-learn.
result Facilitates fast prototyping and algorithm development.
Do-AIQ framework evaluates AI algorithms' quality using DOE.
problem Quality evaluation of AI mislabel detection algorithms.
method Design-of-experiment approach with high-dimensional constraint space design and surrogate modeling.
result Established framework for evaluating AI algorithm quality robustly.
Paper explores cohomology classes on non-compact almost Kähler manifolds.
problem Understanding cohomology classes induced by symplectic forms.
method Provides criteria for non-trivial classes in Lp cohomology. result Symplectic forms induce non-trivial classes in Lp cohomology. A new framework uses deep reinforcement learning to improve aircraft separation in busy airspace.
problem Improving aircraft separation in high-density, dynamic airspace constrained by human controllers.
method Proximal Policy Optimization with an attention network for distributed vehicle autonomy.
result The framework significantly reduces offline training time and increases performance.
Formula for branching coefficients of symmetric pairs.
problem Understanding the action of symmetric pairs on flag varieties.
method Proposes a formula for branching coefficients using HC orbits. result Formula provides a finite number of orbits for the action.
The study redefines algorithmic fairness as a sociotechnical concept.
problem Systemic discrimination in automated decision-making.
method Literature review and sociotechnical analysis.
result Algorithmic fairness should be viewed through a sociotechnical lens.
Explains properties of multisymplectic manifolds.
problem None explicitly stated; focuses on defining and characterizing multisymplectic manifolds.
method Review and introduction of multisymplectic geometry concepts.
result Characterization of multisymplectic manifolds and their Hamiltonian structures.
ROCCO solves Co-Clustering problems efficiently over massive datasets.
problem Simultaneously clustering samples and features in cross-domain datasets.
method Graph-based two-sided representation learning with non-convex optimization.
result ROCCO achieves state-of-the-art performance and is robust to noise.
A new method for Bayesian posterior approximation using greedy particle optimization.
problem Difficulties in obtaining posterior distributions for complex models.
method MMD-FW, which minimizes MMD in a greedy way by the Frank-Wolfe algorithm.
result Shows a linear finite sample convergence bound for MMD-FW.
In this paper, we build an organization of high-dimensional datasets that cannot be cleanly embedded into a low-dimensional representation due to missing entries and a subset of the features being irrelevant to modeling functions of interest. Our algorithm begins by defining coarse neighborhoods of the points and defin…
This paper classifies stablecoin designs to mitigate volatility risks.
problem Mitigating the volatility of stablecoins.
method Systematic design classification, component analysis, and future direction identification.
result Identified strengths and drawbacks of existing stablecoin designs.
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…
Existence of hypersurfaces in warped product manifolds proven.
problem Existence of closed hypersurfaces in warped product manifolds.
method Standard degree theory based on a priori estimates.
result Existence of solutions to prescribed Weingarten curvature equations.
The underlying stochastic nature of the requirements for the Solvency II regulations has introduced significant challenges if the required calculations are to be performed correctly, without resorting to excessive approximations, within practical timescales. It is generally acknowledged by practising actuaries within U…
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…
Open-source Vizier optimizes complex systems for Google and beyond.
problem Optimizing large-scale systems with multiple objectives and constraints.
method Distributed, fault-tolerant, flexible API for blackbox optimization.
result OSS Vizier supports a wide range of optimization problems and is available as open-source.
Novel approach ensures stability of compact schemes for variable PDEs.
problem Ensuring stability of compact schemes for variable coefficient PDEs.
method Difference equation approach to derive stability conditions.
result Derives sufficient condition for unconditional stability.
Algorithm reduces high-dimensional SLB regret by exploiting hidden low-rank structure.
problem High-dimensional stochastic linear bandits with hidden low-rank structure.
method Projective Stochastic Linear Bandit (PSLB) using PCA projection.
result PSLB achieves tighter regret bound and faster convergence.
Sparse matrices are favorable objects in machine learning and optimization. When such matrices are used, in place of dense ones, the overall complexity requirements in optimization can be significantly reduced in practice, both in terms of space and run-time. Prompted by this observation, we study a convex optimization…
Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.
problem Safe reinforcement learning in real environments with disturbance.
method Uses partial prior knowledge and conservative inputs to ensure state constraint satisfaction.
result Guaranteed safety with pre-specified probability in the presence of stochastic disturbance.
Paper proposes a sequential statistical test for comparing imitation learning policies with near-optimal stopping.
problem Challenges in rigorously comparing imitation learning policies due to small sample sizes and potential p-hacking.
method Sequential statistical test that adapts the number of trials based on intermediate results, achieving near-optimal stopping.
result Reduces the number of evaluation trials by up to 32% compared to state-of-the-art baselines, saving significant time and effort.