arXiv research

Bayesian optimization tackles constrained high-dimensional problems with penalties and trust regions.

A method for trust evaluation of devices in human-device coexistence systems.

Adaptive replication improves stochastic function optimization.

New metrics CWSA and CWSA+ improve model evaluation under confidence thresholds.

TRSVR combines SVRG with trust-region for faster optimization.

Study examines how uncertainty visualization affects analyst trust in automated classification systems.

The Social Internet of Things (SIoT), integration of the Internet of Things and Social Networks paradigms, has been introduced to build a network of smart nodes that are capable of establishing social links. In order to deal with misbehaving service provider nodes, service requestor nodes must evaluate their trustworth…

Study shows trust and trustworthiness emerge through reinforcement learning.

Decisions by Machine Learning (ML) models have become ubiquitous. Trusting these decisions requires understanding how algorithms take them. Hence interpretability methods for ML are an active focus of research. A central problem in this context is that both the quality of interpretability methods as well as trust in ML…

TREGO improves EGO for global optimization of high-dimensional problems.

AutoAIViz visualizes AutoAI's model generation process, improving user trust.

Translating machine learning (ML) models effectively to clinical practice requires establishing clinicians' trust. Explainability, or the ability of an ML model to justify its outcomes and assist clinicians in rationalizing the model prediction, has been generally understood to be critical to establishing trust. Howeve…

Synthetic experiments are crucial for assessing causal machine learning methods.

New trust matrix quantifies breakdowns in deep neural networks.

Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many benefits, such as ability to evaluate each resulting policy. However, they usually d…

Study investigates how AI can create and detect deceptive explanations, finding they can fool humans but ML can detect them.

Two multifidelity trust-region methods use low-fidelity models for efficient optimization.

Survey reviews explainability in AI for healthcare, emphasizing trust and transparency.

The paper presents a method to compute trusted confidence bounds for LECs in CPS.

TES optimizes black-box functions efficiently with minimal approximations.

KCoreMotif clusters large networks efficiently by exploiting k-core decomposition and motifs.

Trust-aware MAB improves learning performance by accounting for human deviation.

Study finds visual explanations do not significantly improve human accuracy or trust in model predictions.

Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle the challenge of sparse rewards. Hindsight refers to the algorithm's ability to l…

New method solves optimization problems with stochastic objectives and constraints.

Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet. Denoising is concerned with a different type of data quality and tries to reduce the negative impact of data noise on MT training, in particular, neural MT…

Study finds transparency and model performance metrics increase trust in AutoML systems.

No-knowledge alarms detect misaligned LLM judges without trusting them.

TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.

Study explores fairness in financial deep learning through multi-scale trust quantification.

As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the…

L-C2ST improves local diagnostics for SBI approximations.

DeFi doesn't fully remove trust, showing run risk and personal character's importance.

Study compares high-dimensional BO algorithms on 24 functions.

Trust is a collective, self-fulfilling phenomenon that suggests analogies with phase transitions. We introduce a stylized model for the build-up and collapse of trust in networks, which generically displays a first order transition. The basic assumption of our model is that whereas trust begets trust, panic also begets…

Improved conformal prediction for better conditional coverage of classifier predictions.

Recommending appropriate items to users is crucial in many e-commerce platforms that contain implicit data as users' browsing, purchasing and streaming history. One common approach consists in selecting the N most relevant items to each user, for a given N, which is called top-N recommendation. To do so, recommender sy…

Proposes a Quasi-Newton trust region method for policy optimization in reinforcement learning.

PRCD-MAP learns to trust imperfect priors in causal discovery, improving accuracy and robustness.

Knowing when a classifier's prediction can be trusted is useful in many applications and critical for safely using AI. While the bulk of the effort in machine learning research has been towards improving classifier performance, understanding when a classifier's predictions should and should not be trusted has received …

DarkneTZ protects edge devices from DNN model leaks using TEE and model partitioning.

QUACKIE creates a new benchmark for NLP interpretability.

Two new algorithms solve nonconvex-strongly concave problems efficiently.

AdaScale-TuRBO improves high-dimensional Bayesian optimization by dynamically scaling the GP lengthscale.

Proposes a new trust framework for AI models to maximize utility.

Study finds significant price declines and capital reallocation from centralized to decentralized exchanges after FTX collapse.

Study finds machine learning interpretations are often unstable and unreliable.

Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this …