arXiv research

New algorithm for federated learning without a central server.

New identities lift q-dilogarithm to a more complex algebra.

Critiques causal reductionism in financial studies, suggesting alternative approaches.

We prove a version of the Tits alternative for groups acting on complete, finite rank median spaces. This shows that group actions on finite rank median spaces are much more restricted than actions on general median spaces. Along the way, we extend to median spaces the Caprace-Sageev machinery and part of Hagen's theor…

New trust matrix quantifies breakdowns in deep neural networks.

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

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

Artemis framework improves distributed learning with bidirectional compression and partial participation.

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

This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectio…

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

A new car following model reduces platoon level traffic errors.

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

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…

TRSVR combines SVRG with trust-region for faster optimization.

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 …

Two new algorithms solve nonconvex-strongly concave problems efficiently.

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

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

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

Study shows trust and trustworthiness emerge through reinforcement learning.

We study the motion of a particle in the hyperbolic plane (embedded in Minkowski space), under the action of a potential that depends only on one variable. This problem is the analogous to the spherical pendulum in a unidirectional force field. However, for the discussion of the hyperbolic plane one has to distinguish …

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…

TRUST improves tree models' accuracy while maintaining interpretability.

Proposes a new algorithm for solving optimization problems with stochastic objectives and equality constraints.

TROLL improves RL for LLMs by replacing clipping with a trust region projection.

Bidirectional VAE reduces parameters and improves image tasks.

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

Simplified trust region method reduces representation change during fine-tuning.

The three-state agent-based 2D model of financial markets in the version proposed by Giulia Iori in 2002 has been herein extended. We have introduced the increase of herding behaviour by modelling the altering trust of an agent in his nearest neighbours. The trust increases if the neighbour has foreseen the price chang…

Examining ESG scoring method for reliability.

The traditional social recommendation algorithm ignores the following fact: the preferences of users with trust relationships are not necessarily similar, and the consideration of user preference similarity should be limited to specific areas. A social trust and preference segmentation-based matrix factorization (SPMF)…

We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps av…

A macroeconomic model based on the economic variables (i) assets, (ii) leverage (defined as debt over asset) and (iii) trust (defined as the maximum sustainable leverage) is proposed to investigate the role of credit in the dynamics of economic growth, and how credit may be associated with both economic performance and…

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

Improved traffic forecasting model handles missing data.

Trust lies at the crux of most economic transactions, with credit markets being a notable example. Drawing on insights from the literature on coordination games and network growth, we develop a simple model to clarify how trust breaks down in financial systems. We show how the arrival of bad news about a financial agen…

Report on enhancing trust in ML models with visualizations.

Social trust prediction addresses the significant problem of exploring interactions among users in social networks. Naturally, this problem can be formulated in the matrix completion framework, with each entry indicating the trustness or distrustness. However, there are two challenges for the social trust problem: 1) t…

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…

TS-Insight visualizes Thompson Sampling for better debugging and trust.

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 …

This paper improves privacy in federated learning without a trusted server.

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…

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also pr…

JAXFit speeds up curve fitting on GPUs.