A new algorithm avoids worst-case outcomes in risky contexts.
problem Risk-averse behavior in contextual bandits is challenging.
method Developed a first risk-averse contextual bandit algorithm with online regret guarantees.
result First algorithm with an online regret guarantee for risk-averse contextual bandits.
Paper simplifies balancing weights by relaxing outcome assumptions.
problem Estimating missing outcomes in a target population.
method Relaxes outcome assumptions to simplify balancing weights.
result Balancing weights can be simplified with convex loss and minimum worst-case bias.
Study optimizes identifying the best arm with fixed rounds and Gaussian outcomes.
problem Designing efficient experiments to identify the best arm with fixed rounds and Gaussian outcomes.
method Developed worst-case lower bounds and the GNA-EBA strategy for optimal identification.
result GNA-EBA strategy is asymptotically worst-case optimal.
ISMCTS-BR learns best responses in large games, approximating worst-case performance.
problem Learning robustness to worst-case outcomes in large games.
method ISMCTS-BR, a scalable search-based algorithm for deep reinforcement learning.
result ISMCTS-BR approximates worst-case performance in large games.
Optimal strategy identified for minimizing regret in fixed-budget best arm selection.
problem Minimizing expected simple regret in fixed-budget best arm selection.
method Two-Stage (TS)-Hirano-Imbens-Ridder (HIR) strategy using HIR estimator.
result TS-HIR strategy is asymptotically minimax optimal.
Study evaluates approaches to improve worst-case model performance across patient subpopulations.
problem Improving model accuracy for specific patient subpopulations.
method Comparison of distributionally robust optimization (DRO) and standard learning procedures.
result Standard learning procedures generally outperform DRO approaches for improving model performance across subpopulations.
Optimal algorithm for identifying best-arm with minimal regret.
problem Identifying the best arm in two treatments with limited budget.
method Neyman allocation based on outcome standard deviations.
result Neyman allocation is minimax optimal for simple regret.
RISE learns decisions with sensitive variables, improving worst-case outcomes.
problem Uncertainty and bias in decisions due to delayed sensitive variable data.
method Incorporates sensitive variables offline but not at deployment, using quantile or infimum optimization.
result Improves worst-case outcomes for individuals affected by unavailable sensitive variables.
This paper tackles robust policy learning under concept drifts, improving upon existing methods.
problem Tackles robust policy learning under concept drifts, improving upon existing methods.
method Develops a doubly-robust estimator and a learning algorithm to maximize policy value within a given policy class.
result The proposed algorithm achieves sub-optimality gap of the order κ ( Π ) n − 1 / 2 κ(Π)n^{-1/2} κ ( Π ) n − 1/2 , demonstrating substantial improvement over existing benchmarks. LDP speeds up causal discovery by partitioning, improving VAS recall and runtime.
problem Hard causal discovery in nonparametric settings with exponential complexity.
method Local Discovery by Partitioning (LDP) for causal inference around exposure-outcome pairs.
result LDP yields less biased and more precise estimates than baseline methods.
Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discrimination. We measure discrimination as a violation of multi-differenti…
A framework identifies worst-case decision points in safety-critical scenarios, improving risk assessment by 10 hours.
problem Identifying worst-case outcomes in safety-critical decision-making under uncertainty.
method Explicitly estimating distributions of expected return to identify dead-ends, tuning based on risk tolerance.
result Significantly improves risk assessment, providing indications 10 hours earlier and increasing detection by 20%.
GNA optimally identifies the best arm with small gaps.
problem Best arm identification in fixed-budget settings.
method Generalized Neyman Allocation (GNA) for asymptotically locally minimax optimal BAI.
result GNA's worst-case bounds match the lower and upper bounds in the small-gap regime.
DRUM transfers cardiac arrest models across registries with missing covariates.
problem Clinical prediction models fail when key training covariates are unavailable at deployment.
method DRUM transfers models to target populations with structurally missing covariates, optimizing worst-case predictive performance over unknown target distributions.
result DRUM yields better-calibrated predictions and improved clinical classification performance across sites.
Exact simulation of correlated binary outcomes using PMF constraints and linear programming.
problem Simulating dependent Bernoulli outcomes with specific means and correlations.
method Formulate the problem over the joint Bernoulli PMF, impose constraints, and solve as a linear program. Use convex-hull characterization and truncated-moment completion scheme for feasibility and simulation.
result Exact simulation framework for correlated binary outcomes, providing a convex-hull characterization and truncated-moment completion scheme.
Proposes robust ITRs integrating multiple datasets to handle posterior shift.
problem Posterior shift in conditional outcome distributions between source and target populations.
method Distributionally robust approach with closed-form solution and adaptive uncertainty tuning.
result Achieves superior performance compared to existing methods in simulations and real-data applications.
Optimal decision-making using prediction sets to minimize risk.
problem Using prediction sets optimally for decision-making in uncertain scenarios.
method Decision-theoretic framework that seeks to minimize expected loss against a worst-case distribution.
result ROCP algorithm reduces critical mistakes compared to baselines, especially in costly out-of-set errors.
We present a new approach to the problems of evaluating and learning personalized decision policies from observational data of past contexts, decisions, and outcomes. Only the outcome of the enacted decision is available and the historical policy is unknown. These problems arise in personalized medicine using electroni…
New method uses unlabeled data to improve model robustness across different environments.
problem Learning robust models for new, unseen environments when labeled data are scarce.
method Regularizes model sensitivity to perturbations in covariate means and covariances without requiring labels.
result Empirically validated on physical and physiological datasets, demonstrating improved robustness.
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those…
Paper proposes a new DRL algorithm optimizing Spectral Risk Measures for better risk management.
problem Inconsistencies and conservatism in existing risk measures in DRL.
method Optimizes a broader class of static Spectral Risk Measures (SRM) in DRL.
result Demonstrates improved performance over existing risk-neutral and risk-sensitive DRL models.
New method estimates policy performance under unobserved confounding.
problem Estimating policy performance when decisions depend on unobserved variables.
method Developed worst-case bounds for robust OPE under unobserved confounding.
result Efficient procedure for computing worst-case bounds, proving statistical consistency.
Worst-Case Sensitivity measures model sensitivity to uncertainty set size.
problem Model sensitivity to uncertainty set size in Distributionally Robust Optimization.
method Introducing Worst-Case Sensitivity as a measure of model sensitivity, and deriving closed-form expressions for various uncertainty sets.
result DRO solutions can be sensitive to the family and size of the uncertainty set, and worst-case sensitivity reflects these properties.
SHIFT improves robustness in estimating dose-response functions with heavy-tailed contamination.
problem Outliers bias estimates of average dose-response functions in heavy-tailed data.
method SHIFT combines cross-fit nuisance orthogonalization, Welsch-loss, and defensive OLS refit.
result SHIFT reduces RMSE from 1.03 to 0.33 on localized contamination test.
Proposes a sensitivity framework to handle limited overlap in causal inference.
problem Limited overlap between treated and control groups in observational studies.
method Sensitivity framework based on worst-case confidence bounds on bias introduced by trimming.
result Protects against spurious findings by quantifying uncertainty in regions with limited overlap.
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…
Paper improves worst-case regret bounds for RLSVI in reinforcement learning.
problem Minimizing regret in reinforcement learning with randomized value functions.
method Introduces a clipping variant of Thompson Sampling for RLSVI.
result Achieves a i l d e O ( H 2 S A T ) ilde{\mathrm{O}}(H^2S\sqrt{AT}) i l d e O ( H 2 S A T ) worst-case regret bound. New method for causal inference with complex treatment compositions.
problem Estimating causal effects with compositional treatments.
method Kernel-based covariate functional balancing approach.
result Achieves n \sqrt{n} n -consistency without requiring consistent estimation of weights. The book explores alternatives to worst-case analysis for algorithm performance.
problem Providing strong worst-case guarantees for many algorithms is impossible.
method Surveying and detailing various nuanced analysis approaches.
result More nuanced analysis approaches are needed for fundamental problems.
Optimizes bond portfolios to avoid worst-case losses.
problem Finding the worst-case value of a bond portfolio over a range of yield curves and spreads.
method Solves a convex-concave saddle point optimization problem to find the worst-case value and construct a robust portfolio.
result Constructs a bond portfolio that includes the worst-case value, ensuring robustness against market uncertainties.
A framework for analyzing financial systems under scenario constraints.
problem Quantifying worst-case and best-case performance in financial systems.
method Quantitative automata-based framework integrating event history automata and weighted finance finite automata.
result Exact calculation of upper and lower payoff bounds with interpretable witness event histories.
This paper calculates worst-case target semi-variances for uncertain losses.
problem Managing risk when loss distribution is uncertain and only partial information is known.
method Derives worst-case target semi-variances for symmetric or non-negative losses under uncertainty sets representing investor's undesirable scenarios.
result Closed-form expressions for worst-case target semi-variances are derived.
Paper proposes a new framework for individualized treatment rules that generalize better across different distributions.
problem Existing individualized treatment rules may not generalize well when training and testing distributions differ.
method Distributionally robust individualized treatment rules (DR-ITR) framework that maximizes worst-case value function across close distributions.
result Calibrated DR-ITR outperforms standard ITR in generalizability.
New framework identifies worst-case shifts for predictive resource allocation models.
problem Identifying harmful shifts in predictive models for resource allocation.
method Hierarchical model structure and submodular optimization for worst-case loss.
result Empirical evidence shows divergent worst-case shifts identified by different metrics.
New method uses data augmentation to improve causal effect estimation.
problem Improving causal effect estimation in the presence of hidden confounders.
method Introduces IV-like regression and data augmentation techniques.
result Data augmentation can simulate worst-case scenarios for causal estimation.
Many scientific questions require estimating the effects of continuous treatments. Outcome modeling and weighted regression based on the generalized propensity score are the most commonly used methods to evaluate continuous effects. However, these techniques may be sensitive to model misspecification, extreme weights o…
Proposes a new framework for balancing average- and worst-case performance in machine learning.
problem Robustness issues in machine learning, especially in safety-critical domains.
method Probabilistic robustness framework that balances average- and worst-case performance.
result Effective algorithm balances average- and worst-case performance with lower computational cost.
Study approximates worst-case stock trading under uncertainty, quantifying sensitivity.
problem Maximizing worst-case cost of stock gains and losses under uncertainty.
method Approximates worst-case problem by baseline problem as uncertainty vanishes.
result Value of worst-case problem equals baseline value plus correction term.
Framework for worst-case generation using Wasserstein space optimization.
problem Evaluating robustness and stress-testing systems under distribution shifts.
method Min-max optimization over continuous probability distributions in Wasserstein space.
result Global convergence guarantees for the proposed Gradient Descent Ascent scheme.
New framework for learning policies that converge in out-of-sample regions.
problem Reliable out-of-sample recovery in imitation learning.
method Contractive dynamical systems and recurrent equilibrium networks.
result Policy rollouts converge regardless of perturbations, enabling efficient OOS recovery.
Proposes a fairness criterion for multi-objective optimization in classification.
problem Ensuring fairness in classification models across different groups.
method Formulates a minimax Pareto fairness criterion and provides an optimization algorithm.
result Demonstrates improved fairness compared to existing methods on various real-world datasets.
Develops wcPCA for better low-rank approximations in heterogeneous domains.
problem Worst-case performance of PCA in domains with distributional shifts.
method Unified framework (wcPCA) for worst-case optimization, applied to norm-minPCA and norm-maxregret.
result Empirical and theoretical worst-case optimality for low-rank approximations.
Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation…
The paper analyzes worst-case distortion risk metrics and weighted entropy under partial information.
problem Analyzing worst-case distortion risk metrics and weighted entropy with limited information.
method General distributions, partial information (mean and variance), various entropies and risk measures.
result Provides worst-case results for distortion risk metrics and weighted entropy.
Improves neural network performance by enriching training dataset.
problem Achieving worst-case performance guarantees in neural networks.
method Adapting training dataset during training to reduce worst-case violations.
result Improved worst-case performance guarantees in neural networks.
The study assesses how financial networks resist simultaneous price shocks and calculates the worst-case loss.
problem Resilience of financial networks to simultaneous price fluctuations and default contagion.
method Introduced a concept of default resilience margin, ε*, and computed worst-case systemic loss through linear programming.
result Threshold value ε* determines the maximum amplitude of asset price fluctuations the network can tolerate.
Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information settings are considered. The performance of several existing policies is analyzed, an…
Robust hypothesis testing designs a test for worst-case distributions using kernel methods.
problem Design a robust test for hypothesis testing under uncertainty sets.
method Data-driven uncertainty sets constructed using kernel mean embeddings and maximum mean discrepancy (MMD). Bayesian and Neyman-Pearson settings investigated.
result Proposed robust kernel tests are exponentially consistent and asymptotically optimal.