A new insurance and reinsurance pricing scheme based on realized loss.
problem Determining fair and risk-adjusted insurance premiums.
method Performance-based variable premium scheme with random initial premium adjusted based on realized loss.
result The variable premium scheme reduces reinsurer's total risk exposure compared to expected-value premium.
Dual Variable Learning Rates improve neural network training efficiency.
problem Training neural networks efficiently and effectively.
method DVLR uses different learning rates for correct and incorrect responses, and adjusts rates based on network performance.
result DVLR consistently improves neural network accuracy across different types and domains.
Combines VaR and ES forecasts from a large pool of methods.
problem Combining forecasts from a large pool of VaR and ES methods.
method Adapted interval forecast combination methods, including trimmed means and mixtures approach.
result Trimmed mean combinations, mixtures method, and performance-based weighting delivered strong results.
Study uses machine learning to optimize seismic design parameters.
problem Optimizing seismic design parameters for performance-based design.
method Implementing explainable machine learning models to map design variables and performance metrics, integrated into a genetic optimization algorithm.
result Highly accurate surrogate models (R2> 90%) across diverse building types and hazards, identifying optimal member properties.
Model analyzes OTC market making with reputation feedback.
problem Optimizing electronic OTC liquidity provision considering reputation.
method Developed a stochastic-control model with feedback loops.
result Policy alternates between reputation-building and franchise monetization phases.
Model analyzes how reputation feedback affects OTC market making.
problem Understanding and optimizing OTC market making strategies.
method Developed a stochastic-control model with feedback loops.
result Policy alternates between reputation building and franchise monetization.
Proposes a method to evaluate meta-learning performance based on task similarity.
problem Meta-learning performance evaluation ignores task similarity, leading to biased results.
method Generative approach using Latent Dirichlet Allocation to analyze task similarity.
result The proposed method provides an insightful evaluation of meta-learning algorithms, matching common intuition.
We introduce performance-based regularization (PBR), a new approach to addressing estimation risk in data-driven optimization, to mean-CVaR portfolio optimization. We assume the available log-return data is iid, and detail the approach for two cases: nonparametric and parametric (the log-return distribution belongs in …
DCSO dynamically selects top-performing base detectors for outlier ensembles.
problem Challenges in selecting and combining outlier scores from different detectors.
method DCSO dynamically selects top-performing base detectors based on local k-nearest neighbors.
result DCSO provides consistent performance improvement over static combination approaches.
Paper proposes E/PD-Control for better neural network training.
problem Training efficiency and robustness of CNNs in online data flows.
method E/PD-Control combines feedback PD controller with exponential signal.
result Better learning efficiency and robustness demonstrated experimentally.
FedSmart optimizes federated learning models for non-IID data.
problem Model performance on non-IID data is poor and privacy is at risk.
method FedSmart optimizes models by sharing global gradients and adjusting weights based on local validation set accuracy.
result FedSmart improves model performance by allocating more weight to similar data distributions.
A model predicts how hyperparameters affect pruning performance.
problem Predicting the impact of hyperparameters on pruning performance.
method Phenomenological model using temperature-like and load-like parameters.
result A sharp transition phenomenon in pruning performance.
We consider a class of participation rights, i.e. obligations issued by a company to investors who are interested in performance-based compensation. Albeit having desirable economic properties equity-based debt obligations (EbDO) pose challenges in accounting and contract pricing. We formulate and solve the associated …
A machine learning surrogate model predicts earthquake-induced building responses.
problem Expensive FE model simulations for earthquake damage estimation.
method SVD-based earthquake characterization and machine learning model training.
result Deep neural network provides most accurate predictions of building responses.
Cryptos remained resilient after SVB's collapse, contrary to expectations.
problem Impact of SVB collapse on crypto markets.
method Factual summary, sentiment analysis, and market performance examination.
result Cryptocurrencies showed resilience after SVB's collapse.
Statistical analysis of financial data most focused on testing the validity of Brownian motion (Bm). Analysis performed on several time series have shown deviation from the Bm hypothesis, that is at the base of the evaluation of many financial derivatives. We inquiry in the behavior of measures of performance based on …
We propose a prediction model based on the minority game in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies' past performance. Based on the chosen trading strategy they determine their prediction of the movement for the following time period of…
Deep learning improves sensor performance optimization.
problem Optimizing sensor performance based on key metrics.
method Re-approach non-linear regression using deep learning with Keras and Tensorflow.
result Deep learning models improve sensor performance optimization.
A method estimates causal parameters using a latent variable recovery.
problem Estimating causal parameters in contexts with multiple causes and unobserved confounding.
method Substitute adjustment via recovery of latent variables.
result Substitute adjustment estimates adjusted regression parameters under certain conditions.
This article provides a new representation for pricing adjustments in derivatives.
problem Derivative pricing adjustments and XVA (Expected Value of All Risk) models.
method An Ito SDE/parabolic PDE framework to encapsulate pricing adjustments.
result A new representation that encompasses various past adjustments.
Confounding bias, missing data, and selection bias are three common obstacles to valid causal inference in the data sciences. Covariate adjustment is the most pervasive technique for recovering casual effects from confounding bias. In this paper, we introduce a covariate adjustment formulation for controlling confoundi…
New graphical criteria for efficient covariate adjustment in non-parametric causal models.
problem Estimating population average treatment effects in observational studies using non-parametric causal graphical models.
method Developed new graphical criteria to determine efficient covariate adjustment sets for estimating treatment effects in non-parametric causal graphical models.
result Graphical criteria for efficient covariate adjustment can be applied in both linear and non-parametric causal models.
Investigates adjustments on Lie group crossed modules for gauge theory.
problem Existence and classification of adjustments on crossed modules of Lie groups.
method Differentiation/integration correspondence with infinitesimal adjustments; Lie algebra techniques.
result Infinitesimal adjustments exist if and only if the Kassel-Loday class lies in the image of the Chern-Weil homomorphism.
Model-agnostic interpretation techniques allow us to explain the behavior of any predictive model. Due to different notations and terminology, it is difficult to see how they are related. A unified view on these methods has been missing. We present the generalized SIPA (sampling, intervention, prediction, aggregation) …
New rationalization method avoids spurious correlations.
problem Spurious correlations in rationalization criteria.
method Invariant rationalization using game theory constraints.
result Rationales generalize better and align with human judgments.
We describe principal 3-bundles with adjusted connections using Lie algebras and groupoids.
problem Describing principal 3-bundles with adjusted connections.
method Derived explicit forms of adjustment data for 3-term L∞-algebras, integrated action Lie 3-algebroids to Lie 3-groupoids, and used differential cohomology. result Explicit description of principal 3-bundles with adjusted connections in terms of differential cohomology.
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. U…
New theory connects non-abelian bundle gerbes to abelian ones.
problem Challenges in extending higher gauge theory beyond fake-flat sector.
method Developed a comprehensive theory of adjusted connections on non-abelian bundle gerbes.
result Established a new coordinate-independent formulation of lifting theorem.
Efficient adjustment sets found for cost-minimized causal estimations.
problem Estimating interventional means with minimum cost in causal graphical models.
method Defined cost-adjustment sets, constructed flow networks, and used maximum flow algorithms.
result Minimum cost optimal adjustment sets exist and can be found efficiently.
The paper provides PAC bounds for estimating causal effects using covariate adjustment with a valid set.
problem Estimating causal effects in high-dimensional settings without randomized experiments.
method PAC learning perspective, valid adjustment set, $\eps$-Markov blanket, constraint-based algorithms.
result PAC-bounds the estimation error of covariate adjustment by a term exponential in the size of the adjustment set.
Study optimal adjustment sets for causal policies with hidden variables.
problem Estimating dynamic treatment regimes with hidden variables.
method Developed criteria for graphs without hidden variables to compare estimators, extended to dynamic policies and hidden variables.
result Existence and computation of optimal minimal and globally optimal adjustment sets.
We propose unitary group convolutions (UGConvs), a building block for CNNs which compose a group convolution with unitary transforms in feature space to learn a richer set of representations than group convolution alone. UGConvs generalize two disparate ideas in CNN architecture, channel shuffling (i.e. ShuffleNet) and…
New method estimates treatment effects from high dimensional data.
problem Estimating treatment effects from high dimensional data with confounders.
method Generative modeling approach to backdoor adjustment in variational inference.
result Empirically, estimates interventional likelihood in high dimensional settings.
Improved ARMA-GARCH model for illiquid assets like cryptocurrencies.
problem Inadequate modeling of illiquid assets, especially cryptocurrencies, with traditional ARMA-GARCH models.
method Introducing liquidity-adjusted liquidity jump and diffusion metrics into ARMA-GARCH framework.
result The liquidity-adjusted model improves model fit and volatility sensitivity for cryptocurrencies.
Improved estimator reduces bias in statistical learning models.
problem Asymptotic bias in classic WDRO estimator.
method Adjusted Wasserstein distributionally robust estimator.
result Asymptotic unbiased estimator with smaller MSE.
Develops a method to approximate convexity adjustments for interest rate products.
problem Finding accurate convexity adjustments for interest rate products.
method Uses Malliavin calculus to develop an approximation method.
result Excellent numerical accuracy of the formulas for various interest rate products.
In unsupervised outlier ensembles, the absence of ground truth makes the combination of base outlier detectors a challenging task. Specifically, existing parallel outlier ensembles lack a reliable way of selecting competent base detectors, affecting accuracy and stability, during model combination. In this paper, we pr…
In kernel methods, the median heuristic has been widely used as a way of setting the bandwidth of RBF kernels. While its empirical performances make it a safe choice under many circumstances, there is little theoretical understanding of why this is the case. Our aim in this paper is to advance our understanding of the …
Proposes BA method for unbiased time series anomaly detection evaluation.
problem Anomalies in time series data are rare, making F1-score unreliable.
method Introduces Balanced Point Adjustment (BA) to address F1-score bias.
result BA provides fairer evaluation of time series anomaly detectors.
New risk measures adjust for tail risk inadequacies.
problem Tail risk inadequacy in classical risk measures.
method Developed a family of adjusted risk measures using target risk profiles.
result Analyzed and derived properties of adjusted risk measures.
Risk adjustment has become an increasingly important tool in healthcare. It has been extensively applied to payment adjustment for health plans to reflect the expected cost of providing coverage for members. Risk adjustment models are typically estimated using linear regression, which does not fully exploit the informa…
Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of various input samples being correctly classified are different…
Optimizes treatment duration to maximize quality-adjusted lifetime.
problem Balancing risks and benefits in clinical decision making.
method Proposes a weighted estimating equation to adjust for confounding and informative censoring, and a nonparametric estimator for mean counterfactual quality-adjusted lifetime.
result Shows the optimal time for percutaneous endoscopic gastrostomy insertion in ALS patients.
Model predicts risk-adjusted returns across various financial markets.
problem Stationary models fail in predicting risk-adjusted returns due to market regime changes.
method Asset-independent regime-switching model using hidden Markov models.
result Accurately detects bull, bear, and high volatility periods for improved risk-adjusted returns.
New risk theory for 'Pay-for-Performance' models.
problem How to price and hedge operational and financial risks in new business models.
method Developed a new risk theory and calculation method for 'Pay-for-Performance' models.
result Presented a model for determining risk premiums including both financial and operational risks.
LOAD discovers optimal adjustments locally for scalable causal inference.
problem Scalable causal inference for unknown causal graphs.
method Local Optimal Adjustments Discovery (LOAD) method.
result LOAD combines local and global approaches for efficient and accurate causal effect estimation.
Historical returns depend on historical closing prices and distributions. We describe how to compute adjusted closing prices from closing price/distribution data with an emphasis on spreadsheet implementation. Then the growth of a security from one date to another (1 + total return) is just the ratio of the correspondi…
Estimates model performance from compute budget for distillation.
problem Risk mitigation in large-scale distillation.
method Distillation scaling law based on compute budget allocation.
result Maximizes student performance with compute-optimal allocation.