Study proposes worst+gap measure for better DG evaluation.
problem Lack of comprehensive exploration of average measure in DG evaluation.
method Introduced worst+gap measure and compared it with average measure.
result Worst+gap measure provides a more accurate approximation of true DG performance.
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.
problem Protecting model accuracy in public datasets with diverse learners.
method Formalizes and analyzes LARP, a robust data prefiltering method.
result LARP provides guarantees on worst-case loss over a set of learners, with some performance trade-off.
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.
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.
Researchers solve a market model with stochastic interest rate using worst case approach.
problem Finding the worst case measure for a market with a stochastic interest rate.
method Formulated as a stochastic game, solved using PDE methods and verified with precise argument.
result The worst case measure is not a martingale measure in the given market model.
UCB algorithm's arm-sampling behavior is revealed, leading to new insights and proofs.
problem Optimizing multi-armed bandit algorithms for worst-case scenarios.
method Analysis of UCB algorithm's arm-sampling behavior and process-level characterization.
result UCB's arm-sampling rates are asymptotically deterministic, regardless of problem complexity.
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.
New algorithms improve contextual bandit performance by adapting to problem difficulty.
problem Improving contextual bandit performance on problems with varying difficulty.
method Introducing complexity measures and oracle-efficient algorithms.
result Achieves optimal instance-dependent regret bounds for rich policy classes.
WR-CP reduces prediction set size and coverage gap under distribution shift.
problem Guaranteed coverage under distribution shift not achievable with i.i.d. assumption.
method Wasserstein distance, probability measure pushforwards, importance weighting, regularized representation learning.
result Reduces coverage gap to 3.2% across different confidence levels.
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 Q-learning bounds using reference-advantage decomposition.
problem Improving Q-learning bounds in MDPs with positive suboptimality gaps.
method Develops a novel error decomposition framework to prove gap-dependent regret bounds.
result Establishes logarithmic gap-dependent regret bounds for Q-learning.
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.
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.
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.
The paper refines and generalizes worst-case law invariant convex risk measures.
problem Developing robust convex risk measures under uncertainty sets.
method Generalizing closed forms for worst-case law invariant convex risk measures with uncertainty sets based on norms and moment constraints.
result Explicit closed forms for convex risk measures are developed and assessed through numerical simulations.
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.
problem Risk management, especially in finance.
method Lambda extension of Rényi entropic value-at-risk (Λ-EVaR). Defines properties and provides axiomatic characterization.
result Λ-EVaR bridges adaptive risk tolerance and moment-sensitive risk assessment.
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.
JTT improves model worst-group accuracy without group annotations.
problem Low worst-group accuracy in standard ERM models with spurious correlations.
method Two-stage approach: first ERM, then upweight misclassified examples.
result JTT closes 75% of the gap in worst-group accuracy compared to group DRO.
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 n^{-1/3} n − 1/3 -approximation; 2) NP-hardness of approximatio…
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.
New reinforcement learning algorithm achieves instance-optimal sample complexity.
problem Achieving low regret and identifying optimal policies in reinforcement learning.
method A novel planning-based algorithm that explicitly accounts for state visitation distributions.
result The proposed algorithm attains nearly minimax optimal sample complexity, improving over worst-case bounds.
This research evaluates generalization measures in deep learning.
problem Understanding why deep learning models generalize well despite small training error.
method Empirical evaluation of generalization bounds and measures.
result Generalization measures should be evaluated using distributional robustness.
Improved gap-dependent bounds for reinforcement learning with linear approximations.
problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.
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.
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…
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.
New conditions prevent gaps in optimal control problems.
problem Preventing gaps in optimal control problems with state constraints.
method Developed new sufficient conditions not relying on convexity.
result Derived bounds for the size of the relaxation gap.
New method reduces regret and communication costs in federated Q-learning.
problem Worst-case regret and communication cost bounds in federated Q-learning.
method Gap-dependent analysis leveraging MDP structures.
result Achieves log T \log T log T -type regret and communication cost bounds. MaxMatch improves SSL with worst-case consistency for better generalization.
problem Efficiently supervised learning with unlabeled data.
method Worst-case consistency regularization for SSL, providing a bound and an algorithm.
result The proposed method converges to a stationary point and improves generalization.
New algorithms optimize spectral risk measures, improving interpolation between average and worst-case performance.
problem Optimizing spectral risk measures for learning systems.
method Developed stochastic algorithms to optimize spectral risk measures by characterizing their subdifferential and addressing challenges like biasedness of subgradient estimates and non-smoothness.
result Our approach outperforms out-of-the-box stochastic subgradient and dual averaging methods in optimizing spectral risk measures.
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.
problem Extending classical empirical processes theory to sequential cases.
method Generic chaining, majorizing measures, fractional covering numbers.
result Sharp control of worst-case sequential Rademacher complexity.
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. 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 k k learning iterations admits a lower bound of Ω ( 1 / k ) Ω(1/k) 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.
problem Optimizing vector-valued outcomes with uncertain preferences.
method Stochastic bandit feedback, polyhedral ordering cone, ( ε , δ ε,δ ε , δ )-PAC Pareto set identification. result Sample complexity characterized and matched by the naïve elimination algorithm.
Study online learning in MDPs with aggregate bandit feedback, achieving low regret in both stochastic and adversarial settings.
problem Online learning in finite-horizon episodic MDPs with aggregate bandit feedback.
method Best-of-both-worlds (BOBW) algorithms using FTRL over occupancy measures, self-bounding techniques, and new loss estimators.
result First BOBW algorithms for episodic tabular MDPs with aggregate bandit feedback achieving O ( log T ) O(\log T) O ( log T ) regret in stochastic and O ( T ) {O}(\sqrt{T}) O ( T ) regret in adversarial settings. Improved kernel quadrature with convex weights using subsampling.
problem Constructing quadrature rules with small worst-case error.
method Combining spectral properties of the kernel with recombination results.
result Effective algorithms for constructing convex quadrature rules with i.i.d. samples.
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.
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.
Fine-grained gap-dependent regret bounds for reinforcement learning.
problem Achieving optimal regret bounds for reinforcement learning with suboptimality gaps.
method Developed novel analytical frameworks and refined algorithms for UCB-based and non-UCB-based reinforcement learning.
result Established the first fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms.
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.
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.
Study shows semi-supervised learning can be more robust with fewer labeled examples.
problem Learning robust predictors in semi-supervised PAC model with minimal labeled data.
method Characterizes the minimal labeled and unlabeled data required for robust learning.
result Proves nearly matching upper and lower bounds on labeled sample complexity.
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.
Counterexample shows state-constrained optimal control problems can have Young measure gaps.
problem Existence of Young measure gaps in state-constrained optimal control problems.
method Provided a counterexample for smooth controllable systems state-constrained to the unit ball.
result Gap occurs in a regular setting with non-convex Lagrangian density.