arXiv research

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

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

Improves neural network performance by enriching training dataset.

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

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

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

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

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

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

New approach for pricing evaluation improves on existing methods.

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

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

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

New expressive losses improve adversarial robustness without sacrificing accuracy.

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…

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…

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…

Method identifies shifts leading to large model performance differences.

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

Improved algorithms for stochastic linear bandits using tighter confidence sequences.

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

Efficient learning of minimax risk classifiers in high dimensions.

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…

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…

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

2D Total Variation Denoising (TVD) is a widely used technique for image denoising. It is also an important nonparametric regression method for estimating functions with heterogenous smoothness. Recent results have shown the TVD estimator to be nearly minimax rate optimal for the class of functions with bounded variatio…

LARP filters data to protect model performance across various learners.

We study the performance of data-driven, a priori and random approaches to label space partitioning for multi-label classification with a Gaussian Naive Bayes classifier. Experiments were performed on 12 benchmark data sets and evaluated on 5 established measures of classification quality: micro and macro averaged F1 s…

Optimizes bond portfolios to avoid worst-case losses.

Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case performance, leading to suboptimal performance on easy instances, for example when there ex…

There has been a large amount of interest, both in the past and particularly recently, into the power of different families of universal approximators, e.g. ReLU networks, polynomials, rational functions. However, current research has focused almost exclusively on understanding this problem in a worst-case setting, e.g…

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

Area under ROC curve (AUC) is a widely used performance measure for classification models. We propose two new distributionally robust AUC maximization models (DR-AUC) that rely on the Kantorovich metric and approximate the AUC with the hinge loss function. We consider the two cases with respectively fixed and variable …

New metric measures variability in bandit algorithms, linking regret and variability.

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

Data augmentation methods improve worst-case model performance.

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…

Paper introduces MRCs that minimize worst-case 0-1 loss, providing tight performance guarantees.

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

Algorithms often have tunable parameters that impact performance metrics such as runtime and solution quality. For many algorithms used in practice, no parameter settings admit meaningful worst-case bounds, so the parameters are made available for the user to tune. Alternatively, parameters may be tuned implicitly with…

MRCs minimize worst-case expected 0-1 loss and provide performance guarantees.

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

The problem of data uncertainty has motivated the incorporation of robust optimization in various arenas, beyond the Markowitz portfolio optimization. This work presents the extension of the robust optimization framework for the minimization of downside risk measures, such as Value-at-Risk (VaR) and Conditional Value-a…

Framework for worst-case generation using Wasserstein space optimization.

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

DRCS selects a subset of data to minimize worst-case test error under covariate shift.

This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed …

Study improves communication efficiency in RIS-assisted downlink communication.