arXiv research

Study shows oil prices but not COVID-19 cases affect US economic policy uncertainty.

Paper analyzes mortality risk minimization with and without securitization.

Gaussian process improves nowcasting of COVID-19 deaths.

Deep learning improves death cause coding accuracy.

Method approximates first passage times for birth-death processes.

AI generates a sequence of death causes from hospital records.

Model predicts US COVID-19 deaths with quantile estimates.

Proposes a new birth-death process for better modeling of population dynamics.

Machine learning predicts mask mandates reduce COVID-19 deaths.

Recently we developed a new framework in Hirz et al (2015) to model stochastic mortality using extended CreditRisk$^+$ methodology which is very different from traditional time series methods used for mortality modelling previously. In this framework, deaths are driven by common latent stochastic risk factors which may…

Study shows death ratio of COVID-19 deaths increases financial volatility.

Study identifies clusters of EU countries with similar young mortality patterns.

Jointly models cause-of-death mortality rates across multiple countries and genders.

Study birth-death dynamics for sampling Gibbs measures with nonconvex potentials.

New method evaluates personalized treatment in critical care, robust to death.

New algorithms improve time series prediction with uncertainty quantification.

A new sampling algorithm speeds up Langevin sampling for multimodal distributions.

We find the optimal investment strategy for an individual who seeks to minimize one of four objectives: (1) the probability that his wealth reaches a specified ruin level {\it before} death, (2) the probability that his wealth reaches that level {\it at} death, (3) the expectation of how low his wealth drops below a sp…

ECG signal learning predicts cardiovascular death risk.

Using an extended version of the credit risk model CreditRisk+, we develop a flexible framework with numerous applications amongst which we find stochastic mortality modelling, forecasting of death causes as well as profit and loss modelling of life insurance and annuity portfolios which can be used in (partial) intern…

New method uses birth-death process and exploration component to accelerate sampling from multimodal distributions.

In this paper we present a numerical valuation of variable annuities with combined Guaranteed Minimum Withdrawal Benefit (GMWB) and Guaranteed Minimum Death Benefit (GMDB) under optimal policyholder behaviour solved as an optimal stochastic control problem. This product simultaneously deals with financial risk, mortali…

New birth-death dynamics accelerates convergence in neural networks.

Bayesian networks (BNs) are graphical models that are useful for representing high-dimensional probability distributions. There has been a great deal of interest in recent years in the NP-hard problem of learning the structure of a BN from observed data. Typically, one assigns a score to various structures and the sear…

Looking for associations among multiple variables is a topical issue in statistics due to the increasing amount of data encountered in biology, medicine and many other domains involving statistical applications. Graphical models have recently gained popularity for this purpose in the statistical literature. Following t…

Study quantifies how COVID-19 spread affects US stock markets.

In this paper we study the financial repercussions of the destruction of two fully armed and operational moon-sized battle stations ("Death Stars") in a 4-year period and the dissolution of the galactic government in Star Wars. The emphasis of this work is to calibrate and simulate a model of the banking and financial …

Study uses DNA methylation data to predict suicidal and non-suicidal deaths.

Probabilistic bounds on neuron death in deep networks, showing depth can be increased indefinitely.

New method improves phylogenetic model inference by 30x.

FS&P uses birth-death process to ensure global convergence of stochastic conic particle gradient descent.

Bayesian method learns graph structures from Gaussian data efficiently.

Recently, a marked Poisson process (MPP) model for life catastrophe risk was proposed in [6]. We provide a justification and further support for the model by considering more general Poisson point processes in the context of extreme value theory (EVT), and basing the choice of model on statistical tests and model compa…

Near a birth-death critical point in a one-parameter family of gradient flows, there are precisely two Morse critical points of index difference one on the birth side. This paper gives a self-contained proof of the folklore theorem that these two critical points are joined by a unique gradient trajectory up to time-shi…

Invasive interventions did not significantly shorten ICU patients' time to death.

Study uses machine learning to analyze state drug policies and reduce overdose deaths.

New RL algorithm reduces regret in birth-death queueing problems.

Paper develops a model to predict kidney transplant success.

condLSTM-Q predicts COVID-19 deaths at county level with quantile forecasts.

A framework identifies worst-case decision points in safety-critical scenarios, improving risk assessment by 10 hours.

Study uses artificial counterfactuals to show lockdowns reduced US case and death counts.

Paper disproves conjecture about log-Sobolev constants.

Study on trainability of ReLU networks and proposes data-dependent initialization method.

New MCMC algorithm improves convergence of Bayesian regression trees.

Deep learning predicts Dota 2 deaths with high precision and recall.

Novel method for estimating SIRD model parameters and forecasting COVID-19 deaths in Poland.

Study forecasts COVID-19 cases in Iran using deep learning.

AI system helps clinicians assess liver metastases quickly and with explanations.