arXiv research

Worst-Case Sensitivity measures model sensitivity to uncertainty set size.

Worst-case risk measures refer to the calculation of the largest value for risk measures when only partial information of the underlying distribution is available. For the popular risk measures such as Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR), it is now known that their worst-case counterparts can be ev…

The book explores alternatives to worst-case analysis for algorithm performance.

Paper improves worst-case regret bounds for RLSVI in reinforcement learning.

Optimizes bond portfolios to avoid worst-case losses.

This paper calculates worst-case target semi-variances for uncertain losses.

Proposes a new framework for balancing average- and worst-case performance in machine learning.

New framework identifies worst-case shifts for predictive resource allocation models.

Study approximates worst-case stock trading under uncertainty, quantifying sensitivity.

Framework for worst-case generation using Wasserstein space optimization.

Develops wcPCA for better low-rank approximations in heterogeneous domains.

A new algorithm avoids worst-case outcomes in risky contexts.

The paper analyzes worst-case distortion risk metrics and weighted entropy under partial information.

Improves neural network performance by enriching training dataset.

The study assesses how financial networks resist simultaneous price shocks and calculates the worst-case loss.

Paper derives best- and worst-case GlueVaR measures with incomplete data.

ISMCTS-BR learns best responses in large games, approximating worst-case performance.

Robust hypothesis testing designs a test for worst-case distributions using kernel methods.

Proposes a method to ensure low losses across all subpopulations in large datasets.

Worst-case bounds on the expected shortfall risk given only limited information on the distribution of the random variables has been studied extensively in the literature. In this paper, we develop a new worst-case bound on the expected shortfall when the univariate marginals are known exactly and additional expert inf…

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups). Distributionally robust optimization (DRO) allows us to learn models that instead minimize…

By treating the financial market as a thermodynamic system, we establish a one-to-one correspondence between thermodynamic variables and economic quantities. Measured by the expected loss under the worst-case scenario, financial risk caused by model uncertainty is regarded as a result of the interaction between financi…

In three-dimensional computational topology, the theory of normal surfaces is a tool of great theoretical and practical significance. Although this theory typically leads to exponential time algorithms, very little is known about how these algorithms perform in "typical" scenarios, or how far the best known theoretical…

AI models solved the Kaczmarz algorithm's worst-case complexity.

In this paper we consider the worst-case model risk approach described in Glasserman and Xu (2014). Portfolio selection with model risk can be a challenging operational research problem. In particular, it presents an additional optimisation compared to the classical one. We find the analytical solution for the optimal …

New algorithm reduces worst-case regret for heavy-tailed bandits.

The paper tackles adversarial robustness by maximizing worst-case mutual information.

Proposes a new uncertain volatility model with worst-case scenario analysis.

Options are generally learned by using an inaccurate environment model (or simulator), which contains uncertain model parameters. While there are several methods to learn options that are robust against the uncertainty of model parameters, these methods only consider either the worst case or the average (ordinary) case…

Hardness proof for agnostically learning halfspaces from worst-case lattice problems.

Paper tackles robust online learning with worst-case distributions.

The study assesses external validity by evaluating worst-case treatment effects across subpopulations.

This paper analyzes how randomizing rewards in MBRL can improve performance without being overly optimistic.

We solve robust optimization problem and show the example of the market model for which the worst case measure is not a martingale measure. In our model the instantaneous interest rate is determined by the Hull-White model and the investor employs the HARA utility to measure his satisfaction.To protect against the mode…

Study evaluates approaches to improve worst-case model performance across patient subpopulations.

Study on proper learning under relaxed worst-case robust loss for VC classes.

New approach for pricing evaluation improves on existing methods.

Data augmentation methods improve worst-case model performance.

Quantification of risk positions under model uncertainty is of crucial importance from both viewpoints of external regulation and internal management. The concept of model uncertainty, sometimes also referred to as model ambiguity. Although we know the family of models, we cannot precisely decide which one to use. Give…

The paper refines and generalizes worst-case law invariant convex risk measures.

This paper improves active learning for Gaussian process regression to handle distributional uncertainty.

Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has terrible performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We…

The study assesses ML model robustness under worst-case subpopulations.

We design a general framework for answering adaptive statistical queries that focuses on providing explicit confidence intervals along with point estimates. Prior work in this area has either focused on providing tight confidence intervals for specific analyses, or providing general worst-case bounds for point estimate…

New framework improves worst-case generalization bounds for stochastic optimization.

MaxMatch improves SSL with worst-case consistency for better generalization.

Paper introduces DOO models to outperform SAA out-of-sample.

Bandits with Knapsacks (BwK) is a general model for multi-armed bandits under supply/budget constraints. While worst-case regret bounds for BwK are well-understood, we present three results that go beyond the worst-case perspective. First, we provide upper and lower bounds which amount to a full characterization for lo…