arXiv research

New PAC-Bayes bounds for heavy-tailed losses using supermartingales.

Improved privacy-preserving methods for convex optimization with heavy-tailed data.

Optimizes hybrid insurance contracts for heavy-tailed losses.

Derives derivatives of risk measures for various types of portfolio losses.

Study uses spectral risk for learning with heavy-tailed data.

Improved scalable machine learning under heavy-tailed data.

New algorithms avoid a dominant lower-order term in heavy-tailed loss settings.

Exponential Lasso improves Lasso's robustness to outliers and heavy-tailed noise.

Optimizes privacy-preserving optimization for heavy-tailed data.

Adam outperforms gradient descent on language models due to handling heavy-tailed class imbalance.

New bounds link SGD's generalization to heavy tails without topological assumptions.

Work on SGDm under heavy-tailed noise, revealing its generalization properties.

Heavy Lasso improves robustness in high-dimensional linear regression with heavy-tailed errors.

In this paper, we consider the problem of linear regression with heavy-tailed distributions. Different from previous studies that use the squared loss to measure the performance, we choose the absolute loss, which is capable of estimating the conditional median. To address the challenge that both the input and output c…

Robust biclustering method tackles heavy-tailed data issues.

Paper tackles robust matrix completion with heavy-tailed noise.

The study of heavy-tailed distributions in economic and financial systems has been widely addressed since financial time series has become a research subject.After the eighties, several "highly improbable" market drops were observed (e.g. the 1987 stock market drop known as "Black Monday" and on even more recent ones, …

We improve generative models for heavy-tailed multivariate data using an invariant statistical loss.

The study analyzes a model for aggregate losses with dependent and overdispersed inter-losses times.

We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails. To enable such analyses, we introduce two new conditions: (i) the envelope function $\sup_{f \in \mathcal{F}}|\ell \circ f|$, where $\ell$ is the loss function and $\mathcal{F}$ is the hypothesis class…

We derive PAC-Bayesian learning guarantees for heavy-tailed losses, and obtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds at logarithmic confidence. Our core technique itself makes use of PAC-Bayesian inequalities in order to derive a robust risk estimator, which by design is easy to …

Agents prefer non-diversification in markets with extreme losses.

Heavy-tailed distributions emerge in SGD's parameter evolution.

The paper improves PAC-Bayes bounds for losses with finite moments.

Learning with a {\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper, we study a family of objective functions formed by truncating traditional loss f…

Simplifies risk minimization combining mean and standard deviation.

New method improves mean estimation for heavy-tailed data.

New learning algorithm for heavy-tailed data using CVaR.

Studied how heavy-tailed behavior affects SGD's generalization in quadratic optimization.

New algorithm finds critical points in non-convex optimization with heavy-tailed gradients.

Improved DP SO with large Lipschitz parameters, handling outliers and heavy-tailed data.

Study connects covariance cleaning theory to information theory for heavy-tailed distributions.

The paper explores how benign overfitting occurs in heavy-tailed input distributions.

This work studies applications and generalizations of a simple estimation technique that provides exponential concentration under heavy-tailed distributions, assuming only bounded low-order moments. We show that the technique can be used for approximate minimization of smooth and strongly convex losses, and specificall…

Study improves robust nonparametric regression in heavy-tailed noise.

Privacy-preserving SGD with heavy-tailed noise achieves differential privacy guarantees.

We set the context for capital approximation within the framework of the Basel II / III regulatory capital accords. This is particularly topical as the Basel III accord is shortly due to take effect. In this regard, we provide a summary of the role of capital adequacy in the new accord, highlighting along the way the s…

TailedTS dataset benchmarks heavy-tailed time series forecasting and periodicity quantification.

A new algorithm improves both computational efficiency and statistical optimality for robust low-rank matrix and tensor estimation.

This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise. To deal with heavy-tailed noise whose variance can be infinite, we adopt the quantile regression loss function instead of the commonly used squared loss. However, the non-smooth quantile …

DE-SGD shows heavy-tailed behavior in decentralized settings.

Paper addresses DP-SCO on heavy-tailed data, providing methods and results.

Robust X-Learner improves HTE estimation in imbalanced and heavy-tailed data.

Truncated SGD with heavy-tailed noise eliminates sharp local minima.

Improved robust regression for heavy-tailed and contaminated data.

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…

New study shows diversification can increase risk for heavy-tailed losses.

Under the Basel II standards, the Operational Risk (OpRisk) advanced measurement approach is not prescriptive regarding the class of statistical model utilised to undertake capital estimation. It has however become well accepted to utlise a Loss Distributional Approach (LDA) paradigm to model the individual OpRisk loss…