New algorithms optimize a soft-robust criterion in reinforcement learning, reducing conservatism.
problem Computing robust policies for high-stakes decisions with limited data.
method Soft-robust criterion using risk measures, two algorithms for optimization.
result Our algorithms produce less conservative solutions than existing methods.
The paper examines percentiles of non-identical random variables and provides non-asymptotic bounds.
problem Investigating percentiles of independent but non-identical random variables.
method Analyzing the 100(1−p)%-th percentile X(pn) for a wide class of distributions. result Discovering a connection between the median and the harmonic mean of standard deviations for certain distributions.
Proposes a framework for partially fair machine learning models.
problem Achieving full fairness across all score ranges compromises predictive performance.
method Formulates model training as constrained optimization with difference-of-convex constraints, solvable by IDCA.
result Demonstrates high predictive performance while enforcing partial fairness in specific percentile intervals.
A perturbative approach is used to derive approximations of arbitrary order to estimate high percentiles of sums of positive independent random variables that exhibit heavy tails. Closed-form expressions for the successive approximations are obtained both when the number of terms in the sum is deterministic and when it…
Proposes a method to create shorter, more accurate prediction intervals.
problem Challenges in achieving both conditional validity and interval efficiency in complex settings.
method Uses a conformal-style calibration method for neural network responses, adjusting to empirical PIT distribution.
result Demonstrates better conditional calibration and shorter intervals than existing methods.
Optimizes policies for reinforcement learning with limited data.
problem Computing reliable policies with high confidence in reinforcement learning problems.
method Robust MDPs (RMDPs) with weighted L1 and L∞ norms to minimize ambiguity set spans.
result Optimized ambiguity sets improve policy performance significantly.
We propose a novel non-parametric adaptive anomaly detection algorithm for high dimensional data based on rank-SVM. Data points are first ranked based on scores derived from nearest neighbor graphs on n-point nominal data. We then train a rank-SVM using this ranked data. A test-point is declared as an anomaly at alpha-…
We propose a non-parametric anomaly detection algorithm for high dimensional data. We score each datapoint by its average K-NN distance, and rank them accordingly. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as an anomaly…
We propose a non-parametric anomaly detection algorithm for high dimensional data. We first rank scores derived from nearest neighbor graphs on n-point nominal training data. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as…
Locally adaptive interpretable regression improves linear regression's predictability.
problem Linear regression's predictability is limited; it lacks adaptability.
method Locally adaptive interpretable regression (LoAIR) uses neural networks to predict percentile of a Gaussian distribution for regression coefficients.
result LoAIR achieves comparable or better predictive performance than state-of-the-art baselines.
New models reduce bias in machine learning for credit risk.
problem Bias in machine learning models for credit risk analysis.
method Sum Product Networks (SPNs) to identify and remove independent variables.
result Significant reduction in disparate treatment of male and female applicants.
Novel loss functions improve decision tree learning from noisy data.
problem Training decision trees with noisy labels.
method Introducing distribution losses and a new negative exponential loss.
result The negative exponential loss leads to efficient and robust decision tree learning.
Neural network predicts short rate model steps accurately.
problem Predicting intractable short rate model steps.
method Proposes an algorithm using neural networks.
result Achieves superior outcomes compared to unbiased estimate.
The paper tackles fVaR prediction methods in finance.
problem Predicting future values at risk (fVaR) in finance.
method Various methods including Nested MC-empirical quantile, percentiles from distributions, quantile regressions, and limited inner simulations.
result Improved methods for predicting fVaRs, including those that are computationally efficient.
This paper presents a novel scaling method for unbiased risk estimation.
problem Challenges in risk assessment due to limited data, non-stationarity, and heavy tails.
method Develops a statistical framework for efficient risk scaling, extending beyond the square-root-of-time rule.
result Ensures robust and conservative risk estimation, applicable to small sample settings.
In this paper we discuss a general methodology to compute the market risk measure over long time horizons and at extreme percentiles, which are the typical conditions needed for estimating Economic Capital. The proposed approach extends the usual market-risk measure, ie, Value-at-Risk (VaR) at a short-term horizon and …
Hydropower reduces system electricity price and volatility, especially at extreme levels.
problem Impact of hydropower on system electricity price and volatility.
method Robust statistical analysis using multiple linear regression and quantile regression.
result Hydropower reduces system electricity price and volatility, especially at extreme levels.
We study cross-country GDP losses due to financial crises in terms of frequency (number of loss events per period) and severity (loss per occurrence). We perform the Loss Distribution Approach (LDA) to estimate a multi-country aggregate GDP loss probability density function and the percentiles associated to extreme eve…
We extend the Vasiček loan portfolio model to a setting where liabilities fluctuate randomly and asset values may be subject to systemic jump risk. We derive the probability distribution of the percentage loss of a uniform portfolio and analyze its properties. We find that the impact of liability risk is ambiguous and …
iPrescribe offers fast online offer recommendations using deep learning.
problem Online offer recommendation in real-time.
method Ensemble of deep learning and machine learning algorithms, optimized streaming technology stack, and efficient LSTM deployment.
result 90th percentile recommendation latency of 38 milliseconds.
A distributed RL framework optimizes radio resource management for wireless networks.
problem Interference in wireless networks limits performance; maximizing average and worst-case throughput is challenging.
method Multi-agent deep reinforcement learning (RL) for distributed link scheduling.
result The framework achieves superior average and 5th percentile user throughput compared to decentralized methods.
Optimizes wireless power control using graph neural networks and counterfactual optimization.
problem Mitigating interference in wireless networks with multiple transmitter-receiver pairs.
method Graph neural network architecture combined with unsupervised primal-dual counterfactual optimization.
result Guarantees a minimum rate constraint that adapts to network size, balancing user rates.
We explain how Itô Stochastic Differential Equations (SDEs) on manifolds may be defined using 2-jets of smooth functions. We show how this relationship can be interpreted in terms of a convergent numerical scheme. We show how jets can be used to derive graphical representations of Itô SDEs. We show how jets can be used…
Quantile regression is an increasingly important empirical tool in economics and other sciences for analyzing the impact of a set of regressors on the conditional distribution of an outcome. Extremal quantile regression, or quantile regression applied to the tails, is of interest in many economic and financial applicat…
Investor skill levels affect optimal portfolio size, study shows.
problem Optimal portfolio size for different skill levels of investors.
method Mathematical methods to study annual and continuous portfolio diversification, regression analysis.
result Strong investors should hold concentrated portfolios, poor investors should hold diversified portfolios.
The paper develops bootstrap methods for ACD models with random durations.
problem Bootstrap inference for autoregressive duration models with random durations.
method Recursive schemes for fixed calendar span or realized event count.
result The bootstrap method reproduces the conditional Gaussian component for ACD models with 0<κ<1. Optimizes wireless network resource management with state-augmented policies.
problem Optimizing network-wide utility with user performance constraints.
method State-augmented parameterization of RRM policy, using dual variables.
result Superior trade-off between mean, minimum, and 5th percentile rates.
The paper proposes a method to calibrate evidential clustering using bootstrapped finite mixture models.
problem Representing uncertainty in cluster membership using Dempster-Shafer mass functions.
method Constructing Dempster-Shafer mass functions by bootstrapping finite mixture models, computing confidence intervals, and calibrating the evidential partition.
result The proposed method calibrates the evidential partition such that the belief and plausibility degrees approximate the true probabilities with high confidence.
PRETZEL optimizes machine learning prediction serving systems for better performance.
problem Low latency, high throughput, and graceful performance degradation under heavy load in prediction serving systems.
method Introducing a novel white box architecture enabling both end-to-end and multi-model optimizations.
result Average 5.5x reduction in 99th percentile latency, 25x reduction in memory footprint, and 4.7x increase in throughput compared to state-of-the-art approaches.
Methods for prediction and tolerance intervals in non-normal models.
problem Constructing prediction and tolerance intervals for non-normal data.
method Two approaches: pivotal quantity approximation and confidence interval for mean.
result Intuitive, simple, efficient methods with proper operating characteristics.
Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective fi…
ADB framework improves OOD generalization by increasing ID bias during training.
problem Machine learning models degrade on new data distributions.
method ADB framework introduces controlled statistical diversity during training.
result Higher in-distribution bias leads to better out-of-distribution generalization.
Geometric observables detect financial regime shifts with high accuracy.
problem Detecting regime shifts in financial markets.
method Extracted four geometric observables from equity-index returns and evaluated them against various baseline methods.
result The Berry Phase Rate achieves an unbiased out-of-sample median Cohen's d of 0.72, significantly reducing false alarms.
We propose an analytical approach to the computation of tail probabilities of compound distributions whose individual components have heavy tails. Our approach is based on the contour integration method, and gives rise to a representation of the tail probability of a compound distribution in the form of a rapidly conve…
Potential Future Exposure (PFE) is a standard risk metric for managing business unit counterparty credit risk but there is debate on how it should be calculated. The debate has been whether to use one of many historical ("physical") measures (one per calibration setup), or one of many risk-neutral measures (one per num…
TuNet improves glioma segmentation accuracy and efficiency.
problem Accurate and efficient glioma segmentation for early treatment.
method End-to-end cascaded network with hierarchical structure and ResNet-like blocks.
result Improved segmentation accuracy and reduced treatment costs.
A scalable PyTorch framework for non-crossing quantile regression.
problem Non-crossing quantile regression to avoid impossible negative probability densities.
method CJQR-ALM combining Augmented Lagrangian Method, differentiable pinball loss, and L-BFGS optimization.
result Achieves near-zero crossing rates on large datasets within minutes.
Quantum method speeds up risk estimation for insurance tail risks.
problem Sample-sparsity in classical Monte Carlo methods for tail risk pricing.
method Quantum Amplitude Estimation (QAE) with Grover amplification.
result Quantum method achieves convergence approaching order reciprocal N, enabling high-resolution tail estimation within practical budgets.
Unified framework for comparing classification metrics across different imbalance rates.
problem Differences in scale and sensitivity to class imbalance rates in classification metrics.
method Introduces outperformance standardization (OPS) function to map metrics to a common scale.
result Unified o-value metric provides clear comparison across different imbalance rates.
Neural networks predict shapes of first passage percolation sets.
problem Predicting the shape of first passage percolation sets.
method Used a neural network to predict the shape of the set of discovered sites from the distribution of passage times.
result Neural networks can quickly predict the shape of the set of discovered sites from the distribution of passage times.
Order-flow entropy predicts price magnitude without directionality.
problem Predicting price magnitude in financial markets.
method Real-time order-flow entropy computed from a 15-state Markov transition matrix.
result Order-flow entropy predicts the magnitude of intraday returns with high accuracy.
New framework quantifies uncertainties in neural network explanations.
problem Lack of methods to quantify uncertainties in neural network explanations.
method Converts any explanation method into a Bayesian neural network method, modeling uncertainties.
result Allows quantification of explanation uncertainties and appropriate confidence levels.
Bootstrap method for Markov chains in reinforcement learning.
problem Distributional consistency in finite controlled Markov chains with unknown control policies.
method Model-based bootstrap with novel LLN and CLT for visitation counts and transition increments.
result Asymptotically valid confidence intervals for value and Q-functions in offline RL. Study reveals how dengue spread patterns vary across different years in Recife, Brazil.
problem Understanding spatial organization of dengue transmission in urban areas.
method Spatial analysis of dengue cases using topological data analysis and Vietoris-Rips filtrations.
result Critical percolation thresholds define distinct geometric regimes of dengue spread.
A new policy improvement method using CEM for Actor-Critic.
problem Improving policy efficiency and robustness in reinforcement learning.
method Greedy Actor-Critic (Greedy AC) using Conditional Cross-Entropy Method (CCEM).
result Greedy AC outperforms Soft Actor-Critic and is less sensitive to entropy regularization.
Collage inference uses redundancy to reduce cloud image classification latency variance.
problem Reducing latency variance in cloud image classification.
method Integrates collage-cnn for low-cost redundancy in multi-image classification.
result Significant reduction in 99th percentile tail latency and inference latency variation.
We study an agent-based model of evolution of wealth distribution in a macro-economic system. The evolution is driven by multiplicative stochastic fluctuations governed by the law of proportionate growth and interactions between agents. We are mainly interested in interactions increasing wealth inequality that is in a …
RRPI improves offline RL by optimizing policies against worst-case dynamics.
problem Offline RL's performance degrades under distribution shift and transition uncertainty.
method Formulates offline RL as robust policy optimization, treating transition kernel as decision variable.
result RRPI achieves strong average performance on D4RL benchmarks, outperforming recent baselines.