HD-BWDM improves clustering validation in high-dimensional data.
problem Determining the right number of clusters in high-dimensional data.
method HD-BWDM integrates random projection, PCA, trimmed clustering, and medoid-based distances.
result HD-BWDM remains stable and interpretable under high-dimensional projections and contamination.
The paper presents a method to make predictions robust to distributional shifts.
problem Making predictions robust to distributional shifts in machine learning.
method The method uses prediction sets and conformal inference to provide valid coverage under shifts.
result The method achieves nearly valid coverage in finite samples under exchangeable training data.
Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adver…
Estimates personalized policies robust to shifts in target populations.
problem Estimating policies that perform well in diverse target populations.
method Develops methods for estimating robust policies considering shifts in outcomes and characteristics.
result Welfare-maximizing policies are robust to certain shifts in potential outcomes.
The paper assesses quality measures for machine learning models using cross-validation.
problem Evaluating the accuracy and robustness of quality measures for machine learning models.
method Cross-validation approach to estimate prediction error and quantify explained variation. Confidence bounds and local quality measures derived from residuals.
result The reliability and robustness of quality measures are assessed through numerical examples and confidence bounds.
Replicated and validated Rank-N-Contrast for robust regression.
problem Deep regression models struggle with continuous sample orders.
method Contrastive learning of continuous representations by ranking samples.
result Improved performance and robustness of RNC framework.
Sharp bounds on ATE with unmeasured confounders, valid even when misspecified.
problem Bounding average treatment effects with unmeasured confounders.
method Distributionally robust optimization, double sharpness, double validity.
result Proposes estimators with robustness properties for valid bounds.
Flexible framework integrates machine learning and DRO for uncertain parameter prediction.
problem Limited joint observations of uncertain parameters and covariates.
method Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets.
result Validation of theoretical and practical benefits in limited data scenarios.
Cross-validation under sample selection bias can, in principle, be done by importance-weighting the empirical risk. However, the importance-weighted risk estimator produces sub-optimal hyperparameter estimates in problem settings where large weights arise with high probability. We study its sampling variance as a funct…
Robust variable selection for high-dimensional data with missing and measurement errors.
problem Missing data and measurement errors confound data distribution.
method Exponential loss function with inverse probability weighting and additive error models.
result The Atan punishment method improves robust variable selection.
Paper extends prediction-powered inference using conformal prediction for robust and valid imputation.
problem Safe use of black-box ML models for imputing missing data with strong guarantees.
method Connecting prediction-powered inference with conformal prediction for valid and additional guarantees.
result First general prediction-powered procedure for e-values operating off-line.
Proposes DCV-ROOD framework for robust OOD detection evaluation.
problem Ensuring reliable OOD detection methods under diverse conditions.
method Dual Cross-Validation (DCV) adapted for OOD detection evaluation.
result Demonstrates fast convergence to true performance of OOD detection methods.
This work introduces robust counterfactuals for neural networks that remain valid after minor model changes.
problem Generating counterfactual explanations that are robust to slight model changes.
method Introduces a measure called Stability to quantify robustness of counterfactuals to potential model changes, and proposes practical relaxations.
result Counterfactuals with high Stability remain valid after potential model changes with high probability.
Tests validity of DML estimators without assumptions.
problem Validating DML estimators without making assumptions.
method Develops tests to falsify assumptions for DML estimators.
result Falsifies assumptions for DML estimators with non-trivial power.
AST provides a method to validate safe autonomy without unsafe simplifications.
problem Validation of safe autonomy in complex systems.
method Adaptive Stress Testing (AST) approach.
result AST can find failures without unsafe simplifications.
New method for robust prediction valid under non-exchangeable data.
problem Non-exchangeability in data violates robustness of common CP methods.
method Introduces efficient CP approach for general non-exchangeable data.
result Produces provably valid confidence sets for non-exchangeable data.
The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards this goal have been proposed in recent times, a commonly accepted definition and …
FIRE method improves model performance in federated learning by penalizing fragmentation-induced covariate shifts.
problem Performance degradation in federated learning due to data fragmentation and covariate shift.
method FIRE method accumulates fragmentation-induced covariate shift divergences via approximate Fisher information and uses it as a per-fragment loss penalty.
result FIRE outperforms importance weighting and federated learning benchmarks by up to 5.3% on shifted validation sets.
RILA learns HQMMs robustly against adversarial corruption.
problem Robustness of HQMM learning algorithms under adversarial perturbations.
method Adversarially Corrupted HQMM (AC-HQMM) and Robust Iterative Learning Algorithm (RILA).
result RILA outperforms existing algorithms in convergence stability, corruption resilience, and physical validity.
Paper quantifies label shift robustly.
problem Quantifying label shift in datasets.
method Robust estimators of label distribution.
result Maximum Likelihood Estimator is a robust estimator.
New method clusters variables using robust nodewise regression.
problem Variable clustering in multi-factor models.
method Distributionally robust nodewise regression with convex relaxation and ADMM.
result Superior performance in numerical studies.
Deep RL trains a robust humanoid push-recovery policy.
problem Training robust humanoid push-recovery policies.
method Model-free Deep Reinforcement Learning.
result Policy learns robust behaviors across the entire body.
BREEDS benchmarks assess model robustness to subpopulation shifts.
problem Measuring model robustness to novel subpopulation shifts.
method Controlled synthesis of realistic distribution shifts using class structure.
result Validated model sensitivity and effectiveness of robustness interventions.
ADB framework improves OOD generalization by increasing ID bias during training.
problem Machine learning models degrade on new data distributions.
method ADB framework introduces controlled statistical diversity during training.
result Higher in-distribution bias leads to better out-of-distribution generalization.
Improved scalable machine learning under heavy-tailed data.
problem Machine learning scalability under heavy-tailed data without strong convexity.
method Simple robust validation sub-routine to boost confidence in gradient-based sub-processes.
result Substantial improvement in dimension dependence without strong convexity.
Introduces PCG for better counterfactual explanations in vision models.
problem Ambiguity in latent-space optimization methods for counterfactual explanations.
method Constructs counterfactuals by tracing geodesics under a perceptually Riemannian metric.
result PCG outperforms baselines and reveals hidden failure modes.
Paper introduces DRM for selecting robust CATE estimators.
problem Selecting CATE estimators without counterfactual outcomes.
method Distributionally Robust Metric (DRM) for CATE estimator selection.
result DRM selects robust CATE estimators robust to distribution shift.
Proposes a more robust rating scale for banks.
problem Inconsistent rating scale validation leading to higher capital requirements.
method Develops a new rating scale that is statistically distinguishable and robust.
result Reduces the calibration probability of default, saving capital requirements.
Randomization tests rely on simple data transformations and possess an appealing robustness property. In addition to being finite-sample valid if the data distribution is invariant under the transformation, these tests can be asymptotically valid under a suitable studentization of the test statistic, even if the invari…
The paper develops a method to learn robust decision policies from observational data, reducing high-cost outcomes.
problem Learning safe decision policies from observational data with high-risk outcomes.
method Develops a method to learn policies that reduce high-cost outcomes, valid under finite samples and uneven feature overlap.
result Validates the method with real and synthetic data, providing statistical bounds on decision costs.
Method constructs uniformly valid prediction sets across multiple distributions.
problem Uniformly valid prediction sets across multiple distributions.
method Max-p aggregation scheme and optimization programs.
result Optimal and efficient prediction sets for multiple distributions.
The problem of robust hedging requires to solve the problem of superhedging under a nondominated family of singular measures. Recent progress was achieved by [9,11]. We show that the dual formulation of this problem is valid in a context suitable for martingale optimal transportation or, more generally, for optimal tra…
A new method improves robustness and efficiency of Bayesian LOO-CV.
problem Computational expense and unreliability of classical LOO-CV in high-dimensional Bayesian models.
method Proposes a mixture estimator to compute Bayesian LOO-CV criteria with finite asymptotic variance.
result Improved robustness and efficiency in high-dimensional problems.
SelectMix improves deep learning robustness against noisy labels.
problem Deep neural networks memorize noisy labels, degrading performance.
method Confidence-guided targeted sample mixing with soft labels.
result SelectMix consistently outperforms baseline methods on noisy label datasets.
CNNs achieve remarkable performance by leveraging deep, over-parametrized architectures, trained on large datasets. However, they have limited generalization ability to data outside the training domain, and a lack of robustness to noise and adversarial attacks. By building better inductive biases, we can improve robust…
RoCP-GNN improves GNNs' robustness in graph node classification.
problem Uncertainty in GNN predictions for graph data.
method Integrates conformal prediction into GNN training for robust prediction sets.
result GNN models with size loss improve performance in node classification.
Proposes a method to make statistical inferences robust in spatially dependent settings with missing at random labels.
problem Statistical inference challenges with missing at random labels and spatial dependence.
method Doubly robust estimator with cross-fit nuisances and jackknife spatial HAC variance correction.
result Asymptotically valid confidence intervals with improved finite-sample calibration.
Adaptive auditing improves AI robustness testing with anytime-valid guarantees.
problem Cost and time of annotation limit rigorous AI failure mode characterization.
method Introduces hypothesis testing framework for adaptive audits using SAVI.
result Proves anytime-valid type-I error control and robustness certification.
New method constrains CNN filter frequencies to improve robustness.
problem CNN bias towards low frequency components, leading to poor performance in scenario transformations.
method Frequency domain regularization by constraining filter spectra, training valid frequency range end-to-end.
result Demonstrated effectiveness in defending adversarial perturbations, reducing generalization gap, and improving transfer learning.
Improves reinforcement learning policies for robustness.
problem Lack of robustness in reinforcement learning policies.
method Risk-aware Distributional Reinforcement Learning (SDPG) with CVaR.
result Risk-averse policies achieve robustness against disturbances.
Study robustness of split conformal prediction under adversarial attacks.
problem Ensuring distribution-free coverage guarantees in CP under adversarial conditions.
method Theoretical analysis and extensive experiments on split conformal prediction robustness.
result Prediction coverage varies with calibration-time attack strength, enabling control over coverage under adversarial tests.
New IF method improves accuracy in deep neural networks with noisy data.
problem Inaccurate influence estimates in deep neural networks, especially with noisy data.
method Established a connection between influence estimation error, validation set risk, and sharpness, introducing a novel estimation form for flat validation minima.
result Our novel Influence Function approach provides more accurate influence estimates, validated across various tasks.
Paper proposes a robust hypothesis testing method using Sinkhorn distance.
problem Hypothesis testing for small samples.
method Data-driven approach using Sinkhorn uncertainty sets.
result The method provides a more flexible detector compared to Wasserstein robust test.
New method evaluates personalized treatment in critical care, robust to death.
problem Truncation by death in critical care makes traditional DTR evaluation ineffective.
method Principal stratification-based approach, focusing on always-survivor value function, with a semiparametrically efficient, multiply robust estimator.
result Demonstrates robustness and efficiency of the method for personalized treatment optimization.
Connects robust optimization to conformal prediction for uncertainty sets.
problem Decision-making under uncertainty in sensitive data.
method Defines Mahalanobis distance as a conformity score and generates conformal uncertainty sets.
result Conformal uncertainty sets provide valid and conservative ellipsoidal regions.
Paper optimizes hyperparameters for high-dimensional regression models.
problem Optimizing robustness radius in high-dimensional linear regression.
method Distributionally robust optimization (DRO) with high-dimensional asymptotic statistics.
result Optimal hyperparameter selection minimizes estimation error efficiently.
Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, res…
We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (possibly with overlap across learners) but each trained classifier can be evaluated on a validation dataset. We propose a new approach to aggre…