arXiv research

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

New expressive losses improve adversarial robustness without sacrificing accuracy.

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

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

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

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…

The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce training data, overfitting is typically mitigated by adding regularization term…

We introduce a class of utility-based market makers that always accept orders at their risk-neutral prices. We derive necessary and sufficient conditions for such market makers to have bounded loss. We prove that hyperbolic absolute risk aversion utility market makers are equivalent to weighted pseudospherical scoring …

Optimizes bond portfolios to avoid worst-case losses.

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…

We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10. We obtain verifiable average case and worst case robustness guarantees, based on the expected and maximum values of the…

Method identifies shifts leading to large model performance differences.

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

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…

A new method for survival analysis models that ensures fairness without using sensitive demographic data.

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

LARP filters data to protect model performance across various learners.

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

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…

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

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.

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…

Optimizes privacy-preserving optimization for heavy-tailed data.

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

We introduce a modular framework for market making. It combines cost-function based automated market makers with bandit algorithms. We obtain worst-case profits guarantee's relative to the best in hindsight within a class of natural "overround" cost functions . This combination allow us to have distribution-free guaran…

A new privacy accountant for Gaussian differential privacy measures individual privacy losses.

We consider the problem of learning a loss function which, when minimized over a training dataset, yields a model that approximately minimizes a validation error metric. Though learning an optimal loss function is NP-hard, we present an anytime algorithm that is asymptotically optimal in the worst case, and is provably…

Improves policy optimization with polylog(T) regret bounds for stochastic losses.

Paper aims to ensure reliable detection of out-of-distribution data with certifiable worst-case guarantees.

Paper tackles robust online learning with worst-case distributions.

Optimal decision-making using prediction sets to minimize risk.

MaxUp improves neural network training by minimizing worst case loss.

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

New method calibrates ambiguity sets for robust decision-making under contamination.

Regulator allocates buffers to prevent financial contagion in networks with common assets.

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) m…

New algorithm expands FTRL framework with improved worst-case regret bounds.

Understanding and measuring model risk is important to financial practitioners. However, there lacks a non-parametric approach to model risk quantification in a dynamic setting and with path-dependent losses. We propose a complete theory generalizing the relative-entropic approach by Glasserman and Xu to the dynamic ca…

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

Optimal early liquidation strategy reduces financial losses during crises.

A new notion of stochastic ordering is introduced to compare multivariate stochastic risk models with respect to extreme portfolio losses. In the framework of multivariate regular variation comparison criteria are derived in terms of ordering conditions on the spectral measures, which allows for analytical or numerical…

Improved regret bounds for adversarial linear contextual bandits.

The paper analyzes and proposes methods for privately sharing individual privacy losses using per-instance differential privacy.

We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the autoencoder that reconstructs its inputs with worst-case optimal loss. The optimal decode…

Paper simplifies balancing weights by relaxing outcome assumptions.

We propose to interpret distribution model risk as sensitivity of expected loss to changes in the risk factor distribution, and to measure the distribution model risk of a portfolio by the maximum expected loss over a set of plausible distributions defined in terms of some divergence from an estimated distribution. The…

A robust multiclass SVM tackles imbalanced data uncertainty.