arXiv research

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

Framework for worst-case generation using Wasserstein space optimization.

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

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

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

Improves neural network performance by enriching training dataset.

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

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

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

Optimizes bond portfolios to avoid worst-case losses.

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

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

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…

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

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

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

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

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

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…

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…

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

Paper tackles robust online learning with worst-case distributions.

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

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

This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. B…

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…

Given a task of predicting $Y$ from $X$, a loss function $L$, and a set of probability distributions $Γ$ on $(X,Y)$, what is the optimal decision rule minimizing the worst-case expected loss over $Γ$? In this paper, we address this question by introducing a generalization of the principle of maximum entropy. Applying t…

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

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

Paper proves higher-order flow matching preserves optimality in generative modeling.

Efficient learning of minimax risk classifiers in high dimensions.

SRO optimizes decisions against worst-case sampler induced by generative models.

The paper introduces a new measure of robustness for partially identifiable risks.

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…

Investor optimizes worst-case portfolio in uncertain markets.

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…

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

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

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

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…

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

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

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…

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

We consider the problem of learning a dictionary matrix from a number of observed signals, which are assumed to be generated via a linear model with a common underlying dictionary. In particular, we derive lower bounds on the minimum achievable worst case mean squared error (MSE), regardless of computational 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 …

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