Bounds for randomly shared risk of heavy-tailed loss factors
For a risk vector $V$, whose components are shared among agents by some random mechanism, we obtain asymptotic lower and upper bounds for the individual agents' exposure risk and the aggregated risk in the market. Risk is measured by Value-at-Risk or Conditional Tail Expectation. We assume Pareto tails for the components of $V$ and arbitrary dependence structure in a multivariate regular variation setting. Upper and lower bounds are given by asymptotically independent and fully dependent components of $V$ with respect to the tail index $\alpha$ being smaller or larger than 1. Counterexamples, where for non-linear aggregation functions no bounds are available, complete the picture.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions
Conditional Value-at-Risk (CVaR) is a widely used risk metric in applications such as finance. We derive concentration bounds for CVaR estimates, considering separately the cases of light-tailed and heavy-tailed distribu…
Multi-Armed BanditsOn Empirical Risk Minimization with Dependent and Heavy-Tailed Data
In this work, we establish risk bounds for the Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. We do so by extending the seminal works of Mendelson [Men15, Men18] on the …
Learning TheoryFrom Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGD
Understanding the generalization abilities of modern machine learning algorithms has been a major research topic over the past decades. In recent years, the learning dynamics of Stochastic Gradient Descent (SGD) have bee…
Generalization BoundsLearning without Concentration
We obtain sharp bounds on the performance of Empirical Risk Minimization performed in a convex class and with respect to the squared loss, without assuming that class members and the target are bounded functions or have …
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where the loss function is Lipschitz. Instead, a…