arXiv research

New simulations advise caution in choosing principal components for multivariate functional data.

A new approach to risk-sensitive reinforcement learning tackles computational challenges.

SDF-Bayes finds safe drug combinations safely, balancing optimism and caution.

This study quantifies uncertainty in comparing treatments using RCTs with before-and-after measures.

This survey aims to provide a guide to the literature on topological 4-manifolds. Foundational theorems on 4-manifolds are stated, especially in the topological category. Precise references are given, with indications of the strategies employed in the proofs. Where appropriate we give statements for manifolds of all di…

We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for …

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario, the existing theory requires quadratic over-parametrization as a function of the …

DP synthetic data may inflate statistical test results, caution advised.

Causal ML predicts treatment outcomes, aiding personalized medicine.

This study applies old and new generations of panel unit root tests to test the validity of long-run real interest rate parity (RIP) hypothesis for ten Central and Eastern European Countries (CEECs) with respect to the Euro area and an average of the CEECs' real interest rates, respectively. When the panel unit root te…

This paper considers a time-inconsistent stopping problem in which the inconsistency arises from non-constant time preference rates. We show that the smooth pasting principle, the main approach that has been used to construct explicit solutions for conventional time-consistent optimal stopping problems, may fail under …

This paper presents a lower bound for optimizing a finite sum of $n$ functions, where each function is $L$-smooth and the sum is $μ$-strongly convex. We show that no algorithm can reach an error $ε$ in minimizing all functions from this class in fewer than $Ω(n + \sqrt{n(κ-1)}\log(1/ε))$ iterations, where $κ=L/μ$ is a …

A closed linkage mechanism in three-dimensional space is an object comprising rigid bodies connected with hinges in a circular form like a rosary. Such linkages include Bricard6R and Bennett4R. To design such a closed linkage, it is necessary to solve a high-degree algebraic equation, which is generally difficult. In t…

In cheminformatics, compound-target binding profiles has been a main source of data for research. For data repositories that only provide positive profiles, a popular assumption is that unreported profiles are all negative. In this paper, we caution audience not to take this assumption for granted, and present empirica…

A new mathematical model for the Black-Scholes equation is proposed to forecast option prices. This model includes new interval for the price of the underlying stock as well as new initial and boundary conditions. Conventional notions of maturity time and strike prices are not used. The Black-Scholes equation is solved…

Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showc…

Several statistical and machine learning methods are proposed to estimate the type and intensity of physical load and accumulated fatigue . They are based on the statistical analysis of accumulated and moving window data subsets with construction of a kurtosis-skewness diagram. This approach was applied to the data gat…

Compensation methods correct overestimation of adversarial robustness in neural networks.

Study reveals limitations of fair representation learning methods and cautions against their use in performance-sensitive tasks.

Bayesian approach for learning from synthetic data, improving model accuracy.

Dropout regularizes against high-order interactions by canceling interaction rates.

Noise affects the effectiveness of interpolating models, especially those with strong inductive biases.

Models for which the likelihood function can be evaluated only up to a parameter-dependent unknown normalising constant, such as Markov random field models, are used widely in computer science, statistical physics, spatial statistics, and network analysis. However, Bayesian analysis of these models using standard Monte…

Financial event studies often misestimate causal effects due to misspecified factor models.

Curriculum learning and imitation learning improve control over financial time-series data.

We present two sets of theoretical results on the grouped lasso with overlap of Jacob, Obozinski and Vert (2009) in the linear regression setting. This method allows for joint selection of predictors in sparse regression, allowing for complex structured sparsity over the predictors encoded as a set of groups. This flex…

Recourse explanations can become invalid if collective actions change statistical data.

Study shows GPT's earnings forecasts are human-like but not always accurate.

The paper discusses the importance of infinite-mean models in finance and risk management.

Machine learning confound removal biases results, leading to misleading predictions.

Fan tokens surged before World Cup matches, but declined during them, revealing cognitive biases.

Two XAI methods, SHAP and LIME, are discussed for tabular data models.

Study examines how COVID-19 affected stock and crypto market efficiency.

Boosted additive models reveal new insights and potential pathologies.

RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.

Paper reviews synthetic data from AI models for statistical inference.

The aim of this paper is to study the construction of prospective mortality tables from a low number of persons subjected to risk. The presented models are the Lee-Carter and log-Poisson methods respectively. The low number of people subjected to risk, particularly noticed for the persons who are getting on, implies th…

Study analyzes sensitivity of RL algorithm for ICU hemodynamic management.

New research suggests privileged information doesn't improve model performance.

Proposes minimal interventions over counterfactual explanations for algorithmic recourse.

Langevin dynamics fails to produce accurate samples even with small score function errors.

The paper optimizes LLM inference systems through queueing theory.

Generative text classifiers are most vulnerable to membership inference attacks.

Study finds Deep Taylor Decomposition is unreliable for explaining neural networks.

Novel OTT method for cryptocurrency trading offers high annualized profit.

Publicly pretraining models on Web data may undermine differential privacy.

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many situations it is preferable to delay a decision rather than run the risk of making …

Network-based strategy for optimal cryptocurrency portfolios identified.