A new framework for robust risk measurement and portfolio optimization.
problem Uncertainty in mean-covariance space and portfolio optimization challenges.
method Modeling uncertainty with Gelbrich distance and prior structural information, related to optimal transport theory.
result Mean-covariance robust portfolio optimization simplifies to Markowitz model with a regularization term.
Enhanced Transformer models predict ETF portfolio performance by optimizing covariance and semi-covariance matrices.
problem Static covariance estimates fail to capture dynamic market fluctuations and non-linear correlations.
method Transformer-based models for real-time covariance and semi-covariance predictions.
result Portfolios optimized with semi-covariance matrix outperform those with standard covariance matrix, especially in volatile conditions.
Deep learning improves covariance matrix estimation for better portfolio risk management.
problem Improving the accuracy of covariance matrix estimation for portfolio risk management.
method Formulated as a learning problem, used deep learning to automatically discover risk factors.
result 1.9% higher explained variance and reduced portfolio risk.
Study improves portfolio risk estimation methods using robust covariance and CVaR constraints.
problem Improving portfolio risk estimation in the presence of financial data noise and extreme market conditions.
method Exploration of robust covariance estimators, application of CVaR constraints, use of K-means clustering in optimization.
result Robust covariance estimators can outperform market-weighted benchmarks, especially during bull markets.
The paper addresses portfolio allocation with uncertain covariance matrices, finding a logarithmic risk dependence.
problem Portfolio allocation with uncertain covariance matrices.
method Calculates the expected value of CARA utility function over a distribution of covariance matrices, considering uncertainty in future returns and covariances.
result Marginalization introduces a logarithmic dependence on risk, leading to lower allocation levels for higher uncertainties.
Study forecasts volatility and risk in electricity markets using matrix-HAR models.
problem Forecasting volatility and risk in electricity markets.
method Constructed a parsimonious matrix-HAR type model to estimate realized covariation and risk premia in electricity markets.
result Inclusion of longer time horizons and renewable generation information improves forecasts.
Exact minimax risk derived for linear prediction with sample covariance analysis.
problem Understanding the minimax risk in linear prediction under various covariate distributions.
method Exact minimax risk analysis, leveraging statistical leverage scores and PAC-Bayes techniques.
result The minimax risk is of order d/(n−d+1) for any covariate distribution, nearly matching the risk for Gaussian design. Model predicts operational risk using HMMs with economic covariates.
problem Predicting operational risk losses with time-dependent structures and economic covariates.
method Hidden Markov Models extended to multivariate observations with an auxiliary economic variable.
result Calibration results show relevance of including economic covariates.
Covariance shrinkage via stochastic interpolation
problem High-dimensional covariance estimation
method Recasting shrinkage as empirical risk minimization
result Reduces statistical risk through scheduling, flow maps, and early stopping
The paper analyzes the risk of a least squares estimator under a spike covariance model.
problem Risk analysis of the least squares estimator under a spike covariance model.
method Assumes spike covariance matrices, studies risk as d/nightarrow∞. result Risk of the minimum norm least squares estimator vanishes compared to the null estimator.
New methods improve portfolio risk minimization by estimating covariance matrix more accurately.
problem Uncertainty in estimating covariance matrix leads to unreliable hedge trades.
method Proposes two new estimators of the inverse covariance matrix using l2 and l1 norms.
result Portfolio formed using proposed estimators achieves substantial risk reduction and improved returns.
Paper optimizes trend-following portfolios using autocorrelation models.
problem Developing an optimal trend-following portfolio strategy.
method Introduces a unifying theoretical setting with autocorrelation models for covariance matrices of trends and risk premia. Specifies practical models for covariance matrices. Decomposes optimal portfolio into four basic components.
result Empirical backtests confirm overperformance of the proposed optimal portfolio.
TRACE analyzes risk changes in models trained on shifted data.
problem Understanding performance changes when a model trained on shifted data is used.
method TRACE framework decomposes risk change into four factors: generalization gaps, model change penalty, and covariate shift penalty.
result TRACE provides a diagnostic tool to understand and quantify risk changes due to covariate shift.
This note improves correlation stress tests using geodesic distance.
problem Improving financial risk management through better covariance stress tests.
method Proposes a new geometrically invariant definition of correlation stress tests.
result Demonstrates a submanifold approach to stress testing covariance matrices.
Develops a hedging method for multi-asset derivatives with correlation risk.
problem Hedging multi-asset derivatives exposed to correlation and covariance risk.
method Combines dynamic trading with static hedging instruments using Galtchouk--Kunita--Watanabe decomposition.
result Explicit semi-static replication formulas for covariance swaps and geometric dispersion trades.
In this paper, we obtain a property of the expectation of the inverse of compound Wishart matrices which results from their orthogonal invariance. Using this property as well as results from random matrix theory (RMT), we derive the asymptotic effect of the noise induced by estimating the covariance matrix on computing…
We give a simple explicit algorithm for building multi-factor risk models. It dramatically reduces the number of or altogether eliminates the risk factors for which the factor covariance matrix needs to be computed. This is achieved via a nested "Russian-doll" embedding: the factor covariance matrix itself is modeled v…
The paper introduces MRVaR and MRCov for elliptical and log-elliptical distributions.
problem Risk management of regulation and investment purposes.
method Proposes MRVaR and MRCov as risk measures for elliptical and log-elliptical distributions.
result Explicit expressions of MRVaR and MRCov derived for multivariate (log-)elliptical distributions.
NICE learns a representation to avoid bad controls in causal inference.
problem Avoiding bad controls in causal inference from observational data.
method Uses invariant risk minimization (IRM) to learn a representation of covariates that avoids bad controls.
result NICE outperforms adjusting for all covariates in cases with unknown collider variables and bad controls.
Shrunk sample covariance matrix is a factor model of a special form combining some (typically, style) risk factor(s) and principal components with a (block-)diagonal factor covariance matrix. As such, shrinkage, which essentially inherits out-of-sample instabilities of the sample covariance matrix, is not an alternativ…
We propose a framework for constructing factor models for alpha streams. Our motivation is threefold. 1) When the number of alphas is large, the sample covariance matrix is singular. 2) Its out-of-sample stability is challenging. 3) Optimization of investment allocation into alpha streams can be tractable for a factor …
Forecast reconciliation improves portfolio risk forecasts, especially when true covariance is known.
problem Improving portfolio risk forecasts using multivariate GARCH models.
method Combining univariate and multivariate forecasts with forecast reconciliation techniques.
result Forecast reconciliation improves over standard multivariate approaches, especially when true covariance is known.
New methods estimate survival functions with time-varying covariates.
problem Estimating survival functions with time-varying covariates.
method Generalized conditional inference and relative risk forests, adapted transformation forest.
result Proposed methods outperform traditional models in estimating survival functions.
We provide a unified analysis of the predictive risk of ridge regression and regularized discriminant analysis in a dense random effects model. We work in a high-dimensional asymptotic regime where p,n→∞ and p/n→γ∈(0,∞), and allow for arbitrary covariance among the features. For both metho…
Proposes spBART for risk prediction using epigenetic signatures and covariates.
problem Complex high-dimensional epigenetic data and low-dimensional covariates for risk prediction.
method Semi-parametric Bayesian Additive Regression Trees (spBART) with cross-validation for variable selection.
result Achieves strong out-of-sample discrimination (AUC = 0.96) in held-out validation set.
Evaluating prediction models under covariate shift and selective labels
problem Model performance evaluation under distribution shift and selection bias
method Double machine learning
result Accurate estimation of target risk
Study variance-optimal hedging of forward curve derivatives under stochastic volatility.
problem Variance-optimal hedging of forward curve derivatives with stochastic volatility.
method Assumes HJM-Musiela dynamics modulated by stochastic covariance, uses Galtchouk-Kunita-Watanabe projection.
result Density of finite-maturity strategies, convergence of finite-rank projections, decomposition of hedging error.
High precision analytical approximation is proposed for variance-covariance based risk allocation in a portfolio of risky assets. A general case of a single-period multi-factor Merton-type model with stochastic recovery is considered. The accuracy of the approximation as well as its speed are compared to and shown to b…
We propose an approach to the aggregation of risks which is based on estimation of simple quantities (such as covariances) associated to a vector of dependent random variables, and which avoids the use of parametric families of copulae. Our main result demonstrates that the method leads to bounds on the worst case Valu…
A new one-step method for covariate shift adaptation.
problem Real-world data often violates the assumption of same distribution for training and test samples.
method Proposes a one-step optimization approach to jointly learn the model and weights.
result The proposed method achieves a generalization error bound and is empirically effective.
The paper develops methods to reduce deployment risk under dynamic covariate shifts.
problem Reduction of deployment risk under dynamic covariate shifts.
method Time-domain Poincare inequality and Jacobian-velocity theorem to identify and control directional tangent energy.
result Drift-aligned tangent regularization (DTR) reduces risk volatility and directional gain in low-rank drift regimes.
We give a complete algorithm and source code for constructing what we refer to as heterotic risk models (for equities), which combine: i) granularity of an industry classification; ii) diagonality of the principal component factor covariance matrix for any sub-cluster of stocks; and iii) dramatic reduction of the facto…
Study non-asymptotic estimation bounds for LTI models with Gaussian noise.
problem Estimating parameters of LTI models with non-asymptotic error bounds.
method Sharp non-asymptotic lower bounds using Cramér-Rao and van Trees inequalities, concentration results, and differential geometric constructions.
result Sharp and rate-optimal lower bounds for mean square estimation risk.
We propose a route for the evaluation of risk based on a transformation of the covariance matrix. The approach uses a `potential' or `objective' function. This allows us to rescale data from different assets (or sources) such that each data set then has similar statistical properties in terms of their probability distr…
Maximum likelihood estimator performance in logistic regression analyzed.
problem Performance of maximum likelihood estimator in logistic regression.
method Sharp non-asymptotic guarantees for existence and excess logistic risk.
result Sharp guarantees for the existence and excess risk of MLE in logistic regression.
Neural network method estimates covariate-dependent graphical models with statistical guarantees.
problem Estimating graph structure from covariate-dependent data.
method Neural network approach that allows flexible functional dependency on covariates.
result Theoretical PAC guarantees for the method's performance.
Enhances Cox model for survival analysis with symbolic non-linear log-risk functions.
problem Limited interpretability and non-linearity in traditional Cox models.
method Introduces GCPH model using Kolmogorov-Arnold Networks for symbolic non-linear log-risk functions.
result GCPH achieves competitive performance and superior interpretability.
REx tackles distributional shift by reducing risk differences across domains.
problem Tackling distributional shift when transferring machine learning systems to real-world applications.
method Risk Extrapolation (REx) assumes training domains represent test-time variations and uses extrapolated domains to minimize risk variance.
result REx reduces sensitivity to extreme distributional shifts, including causal and anti-causal inputs.
Study reveals benign overfitting in time series models with over-parameterization.
problem Analyzing over-parameterized linear models with dependent time-series data.
method Developed an estimator using interpolation and derived non-asymptotic risk bounds.
result Risk bound is influenced by the coherence of temporal covariance matrices at different time steps.
We give an explicit algorithm and source code for constructing risk models based on machine learning techniques. The resultant covariance matrices are not factor models. Based on empirical backtests, we compare the performance of these machine learning risk models to other constructions, including statistical risk mode…
A new method for distilling predictions from a teacher model to a student model without original training data.
problem Training without original labeled data.
method Prediction-only distillation scheme for linear and logistic regression.
result Prediction mixing can outperform both the teacher and pure-distilled models.
Reverses simplification of risk measurement, focusing on portfolio covariance.
problem Risk measurement for unbenchmarkable global funds.
method Principal Component Analysis (PCA) with AI-generated labels, density-based clustering, and risk scores.
result Reveals true risk factors and identifies slow capital destroyers.
CASP improves portfolio optimization by considering asset covariance.
problem Infeasibility in cardinality-constrained portfolio optimization.
method CASP uses volatility-normalized selection and covariance-aware projection.
result CASP-Basic delivers lower portfolio variance than standard Euclidean repair.
Study shows pretraining and finetuning can effectively tackle covariate shift in linear regression.
problem Linear regression under covariate shift where source and target distributions differ but conditional distribution remains similar.
method Pretraining on source data and finetuning on target data using online SGD.
result Transfer learning with O(N2) source data is as effective as supervised learning with N target data. Method estimates joint distribution of bivariate outcomes.
problem Modeling dependence between bivariate outcomes.
method Semiparametric distribution regression.
result Method performs similarly or better than alternatives in finite samples.
The use of improved covariance matrix estimators as an alternative to the sample estimator is considered an important approach for enhancing portfolio optimization. Here we empirically compare the performance of 9 improved covariance estimation procedures by using daily returns of 90 highly capitalized US stocks for th…
Study optimal ridge regularization for out-of-distribution prediction.
problem Optimal ridge regularization for predicting out-of-distribution data.
method Established conditions for optimal regularization under covariate and regression shifts, proving monotonic risk in data aspect ratio.
result Negative regularization can be optimal under shifts, even with isotropic or underparameterized training features.
We study the design of portfolios under a minimum risk criterion. The performance of the optimized portfolio relies on the accuracy of the estimated covariance matrix of the portfolio asset returns. For large portfolios, the number of available market returns is often of similar order to the number of assets, so that t…