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.
Closed-form solutions for worst-case law invariant risk measures simplify risk analysis.
problem Calculating worst-case risk measures with limited distribution information.
method Developed closed-form solutions for law invariant coherent risk measures.
result Similar closed-form solutions exist for law invariant risk measures as for CVaR.
New algorithm reduces worst-case regret for heavy-tailed bandits.
problem Stochastic Multi-Armed Bandit problem with heavy-tailed rewards.
method Modified minimax policy MOSS with saturated empirical mean.
result Worst-case regret matching lower bound for heavy-tailed distributions.
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.
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.
Paper derives best- and worst-case GlueVaR measures with incomplete data.
problem Risk measurement with limited information and shape constraints.
method Unified framework based on partial distribution information and shape properties.
result Characterization of extremal GlueVaR distributions with convex envelopes.
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.
This paper improves active learning for Gaussian process regression to handle distributional uncertainty.
problem Active learning for Gaussian process regression does not guarantee accurate predictions for target distributions.
method Proposes two methods to reduce worst-case expected error for Gaussian process regression.
result Shows an upper bound of the worst-case expected squared error, suggesting finite data labels can achieve arbitrarily small error.
Hardness proof for agnostically learning halfspaces from worst-case lattice problems.
problem Agnostically learning halfspaces in the presence of noise.
method Reduction to worst-case lattice problems (GapSVP, SIVP).
result No efficient algorithm can achieve misclassification error better than 1/2 - γ under given hardness assumptions.
The paper analyzes extreme risk measures with limited distributional information.
problem Investigating risk measures under partial knowledge of distribution moments and shape.
method Employing probability inequalities and modified Schwarz inequality to derive bounds on distortion risk measures.
result Unified framework for calculating best- and worst-case scenarios of distortion risk measures.
Paper tackles robust online learning with worst-case distributions.
problem Distributionally robust online learning with worst-case Wasserstein ambiguity sets.
method Formulated as an online saddle-point stochastic game, proposed a general framework converging to robust Nash equilibrium.
result Proposed a tailored algorithm for piecewise concave loss functions, achieving substantial speedups.
The paper tackles adversarial robustness by maximizing worst-case mutual information.
problem Training robust machine learning models against adversarial inputs is challenging.
method Develops a notion of representation vulnerability and an unsupervised learning method to maximize worst-case mutual information.
result Proves a lower bound on minimum adversarial risk and supports robustness of representations.
DRCS selects a subset of data to minimize worst-case test error under covariate shift.
problem Selecting a subset of data that performs well across different deployment scenarios when data distributions differ.
method DRCS derives an upper bound for the worst-case test error assuming covariate shift and selects instances to minimize this bound.
result DRCS achieves distributionally robust training instance selection.
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.
New regularization techniques using mass transportation for better generalization.
problem Mitigating overfitting with scarce data.
method Distributionally robust optimization and worst-case expected loss.
result Generalization bounds and tractable learning problems.
Solves worst-case joint distribution problem for financial risk factors.
problem Finding worst-case joint distribution of risk factors given marginals and loss function.
method Uses linear programming to solve the problem when CVaR is the risk measure and distributions are discretized.
result Demonstrates method's applicability to various financial contexts, including counterparty credit risk.
Paper solves DRO for continuous distributions with iterative algorithms.
problem Distributionally robust optimization with continuous worst-case distributions.
method Iterative algorithm for global convergence, leveraging Brenier's theorem and JKO scheme.
result Achieves global convergence under mild assumptions for minimax problems.
Develops a method to optimize worst-case objectives using Bayesian optimization.
problem Optimizing in the worst case over a class of non-convex objectives.
method Reduction from robust improper optimization to Bayesian optimization, followed by de-randomization for specific tasks.
result Shows that de-randomizing the solution is NP-hard in general but feasible for certain tasks.
Efficient algorithm for estimating target mean under known sampling distribution.
problem Statistical estimation under known sampling distribution without distributional assumptions.
method Worst-case analysis of weighted combination of sample values.
result Worst-case expected error is at most a π/2 factor worse than optimal.
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.
Study on communication limits for distributed convex learning and optimization.
problem Identifying communication efficiency limits for distributed convex learning and optimization.
method Analyzing different assumptions and types of functions under varying information and computational power.
result Many communication rounds may be required without similarity between local objective functions.
The study assesses ML model robustness under worst-case subpopulations.
problem ML model performance degradation under non-training population.
method Two-stage estimation procedure for evaluating worst-case robustness over subpopulations.
result The method certifies model robustness and prevents unreliable deployments.
This paper calculates worst-case VaR for financial markets using empirical data and model uncertainty.
problem Quantifying risk under model uncertainty for financial risk management.
method Proposed a two-layer mixed distribution model to simplify model uncertainty, used change point detection and EM algorithm for estimation.
result Calculated VaR, WVaR, and BVaR for four financial markets, analyzed their performance.
Develops a new worst-case bound on expected shortfall with bivariate expert information.
problem Bounding expected shortfall with limited distributional information.
method Modeling trade-off between conservatism and expert information using Kullback-Leibler divergence.
result Bound reduces to comonotonic upper bound as expert information becomes more certain.
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.
AdMRL improves meta-reinforcement learning by minimizing worst-case sub-optimality gap.
problem Meta-reinforcement learning's sensitivity to task distribution shift.
method Model-based adversarial approach with minimax objective and alternating optimization.
result Efficacy in worst-case performance, generalization to out-of-distribution tasks, and sample efficiency.
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.
New policy optimizes risk and optimality in stochastic bandits.
problem Optimizing risk in stochastic bandits with heavy-tailed risk.
method Designing policies with worst-case optimality for expected regret and light-tailed risk distribution.
result Achieves worst-case optimality for expected regret and light-tailed risk distribution.
Method identifies shifts leading to large model performance differences.
problem Detecting shifts in distribution that affect model performance.
method Parametric changes in causal mechanisms define robustness sets; worst-case optimization problem approximated as non-convex quadratic.
result Second-order approximation of worst-case loss for small shifts, leading to efficient algorithms.
This paper derives lower bounds on the worst case MSE of dictionary learning schemes.
problem Learning a dictionary matrix from observed signals with a common underlying dictionary.
method Information-theoretic approach to minimax estimation for DL problem.
result Derives three lower bounds on the worst case MSE of DL schemes.
Paper aims to ensure reliable detection of out-of-distribution data with certifiable worst-case guarantees.
problem Deep neural networks are overconfident with OOD inputs, posing safety risks.
method Enforces low confidence and bounds in an l ∞ l_\infty l ∞ -ball around OOD points using interval bound propagation (IBP). result Certifiable worst-case guarantees for OOD detection are possible without significant loss in accuracy.
The paper introduces a minimax approach to supervised learning problems.
problem Optimal decision rule minimizing worst-case expected loss over probability distributions.
method Generalization of maximum entropy principle applied to constrained distributions.
result Developed a new linear classifier called the maximum entropy machine.
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.
DRO optimizes decisions under uncertain distributions, considering worst-case scenarios.
problem Optimizing decisions when the distribution of uncertainties is itself uncertain.
method Defines ambiguity sets and seeks decisions optimal under the worst-case distribution.
result DRO models can be connected to regularization techniques and machine learning.
The paper introduces a new measure of robustness for partially identifiable risks.
problem Achieving robustness when the robust risk is only partially identified.
method Introduces the worst-case robust risk and evaluates existing methods.
result Existing robustness methods are suboptimal in the partially identifiable case.
Federated learning uses worst-case optimization to handle uncertain local data impacts.
problem Handling uncertainty in local data sets in federated learning.
method Reformulate FL problem using worst-case optimization theory, considering local data as uncertain functions bounded in a closed region.
result Comparison of FL performance with centralized learning and application of regularization factors.
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%.
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…
Study improves communication efficiency in RIS-assisted downlink communication.
problem Improving performance of RIS-aided downlink communication over heterogeneous designs.
method Distributed learning with distributionally robust optimization.
result Our algorithm achieves 50% fewer communication rounds for similar worst-case performance.
The paper calculates bounds for risk metrics and entropies under partial information constraints.
problem Analyzing risk metrics and entropies for unimodal, symmetric distributions with limited information.
method Develops lower and upper bounds for worst-case distortion riskmetrics and weighted entropy for unimodal, symmetric distributions with known mean and variance.
result Sharp upper bounds for distortion riskmetrics and weighted entropy for symmetric distributions.
Optimizes regret distribution in stochastic bandits for risk balance.
problem Balancing regret expectation and tail risk in stochastic bandits.
method Characterizes optimal regret tail probability for any threshold, proposes new policies.
result Discovers an intrinsic gap in optimal tail rate based on time horizon uncertainty.
Paper proves higher-order flow matching preserves optimality in generative modeling.
problem Theoretical guarantees for higher-order flow matching in generative modeling.
method Neural network approximations with controlled depth, width, and sparsity.
result Proves worst case optimality for second-order flow matching.
We bridge statistical and worst-case approaches to experimental design for linear regression.
problem Designing efficient experiments for linear regression models with arbitrary responses.
method Propose a new experimental design framework for arbitrary response distributions, combining statistical and worst-case approaches.
result Develop efficient randomized design procedures achieving strong variance bounds for unbiased estimators using few responses.
Data augmentation methods improve worst-case model performance.
problem Ensuring fair predictions across subpopulations in large models.
method Linear last layer retraining with data augmentation techniques.
result Optimal worst-group accuracy achieved for Gaussian latent representation distribution.
A scheme robust to action erasures improves MAB performance.
problem Learning in multi-arm bandits with erasure channels.
method Proposes a scheme to work on top of any MAB algorithm.
result Worst-case regret is at most a factor of O ( 1 / 1 − ε ) O(1/\sqrt{1-ε}) O ( 1/ 1 − ε ) away from no-erasure case. Proposes data-dependent dispatching for improved distributed machine learning accuracy.
problem Improving accuracy in distributed machine learning with data dispatching.
method Data-dependent dispatching, provable algorithms, fault tolerance, balancedness.
result Significantly higher accuracy on synthetic and real-world datasets compared to random partitioning.
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. New method assesses financial and cyber risks under uncertainty.
problem Uncertainty in risk assessment for financial and cyber systems.
method Combines stochastic approximation and distorted mix method to compute worst case average value at risk.
result Efficient algorithm for tail uncertainty in multivariate distributions.