arXiv research

Study proposes worst+gap measure for better DG evaluation.

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…

LARP filters data to protect model performance across various learners.

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

GNA optimally identifies the best arm with small gaps.

UCB algorithm's arm-sampling behavior is revealed, leading to new insights and proofs.

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

New algorithms improve contextual bandit performance by adapting to problem difficulty.

WR-CP reduces prediction set size and coverage gap under distribution shift.

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

This paper improves Q-learning bounds using reference-advantage decomposition.

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

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

Paper solves DRO for continuous distributions with iterative algorithms.

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

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…

Adversarial robustness research primarily focuses on L_p perturbations, and most defenses are developed with identical training-time and test-time adversaries. However, in real-world applications developers are unlikely to have access to the full range of attacks or corruptions their system will face. Furthermore, wors…

Paper introduces Lambda EVaR, a new risk measure.

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

JTT improves model worst-group accuracy without group annotations.

It is well known that Sparse PCA (Sparse Principal Component Analysis) is NP-hard to solve exactly on worst-case instances. What is the complexity of solving Sparse PCA approximately? Our contributions include: 1) a simple and efficient algorithm that achieves an $n^{-1/3}$-approximation; 2) NP-hardness of approximatio…

The paper analyzes extreme risk measures with limited distributional information.

New reinforcement learning algorithm achieves instance-optimal sample complexity.

This research evaluates generalization measures in deep learning.

Improved gap-dependent bounds for reinforcement learning with linear approximations.

AdMRL improves meta-reinforcement learning by minimizing worst-case sub-optimality gap.

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…

New conditions prevent gaps in optimal control problems.

Optimizes regret distribution in stochastic bandits for risk balance.

New method reduces regret and communication costs in federated Q-learning.

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

New algorithms optimize spectral risk measures, improving interpolation between average and worst-case performance.

A new method is proposed to compute connectivity measures on multivariate time series with gaps. Rather than removing or filling the gaps, the rows of the joint data matrix containing empty entries are removed and the calculations are done on the remainder matrix. The method, called measure adapted gap removal (MAGR), …

Majorizing measures control sequential complexities for online learning.

This paper tackles robust policy learning under concept drifts, improving upon existing methods.

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of $Ω(1/k)$. However, prior work using an unregularized scheme has only established an up…

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…

New method for identifying best designs in vector optimization with uncertain feedback.

Study online learning in MDPs with aggregate bandit feedback, achieving low regret in both stochastic and adversarial settings.

Improved kernel quadrature with convex weights using subsampling.

In the presence of model risk, it is well-established to replace classical expected values by worst-case expectations over all models within a fixed radius from a given reference model. This is the "robustness" approach. We show that previous methods for measuring this radius, e.g. relative entropy or polynomial diverg…

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

Fine-grained gap-dependent regret bounds for reinforcement learning.

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…

Framework for worst-case generation using Wasserstein space optimization.

Study shows semi-supervised learning can be more robust with fewer labeled examples.

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

Counterexample shows state-constrained optimal control problems can have Young measure gaps.