Robust test for distributions under Hellinger distance, simpler than optimal tests.
problem Testing and estimating distributions robustly under Hellinger distance.
method Simple robust hypothesis test with optimal sample complexity, robust to Hellinger distance perturbations.
result Empirically demonstrated robustness and power of the test on canonical distributions.
Robust tests control type I error under data corruption.
problem Effective hypothesis testing under data corruption.
method General permutation tests using kernel MMD and HSIC metrics.
result Robust tests are minimax optimal and outperform private tests.
Study robust hypothesis testing under Hellinger distance, proving lower bounds and providing tests.
problem Testing close variants of specified distributions robustly to Hellinger distance.
method Lower bound on slack factor, testing with Hellinger balls, symmetric chi-squared distance analysis.
result Lower bound on slack factor quantifies robustness under misspecification.
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 robustness test for kernel goodness-of-fit tests.
problem Lack of robustness in existing kernel goodness-of-fit tests.
method Proposes a new robust kernel goodness-of-fit test using kernel Stein discrepancy (KSD) balls.
result First robust kernel goodness-of-fit test addressing both qualitative and quantitative robustness.
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.
Paper proposes a robust test for high-dimensional models with large covariates and instruments.
problem Testing high-dimensional linear instrumental variable models with large covariates and instruments.
method Introduces a test based on the maximum norm of multiple parameters and a power-enhanced test.
result The proposed test is robust to heteroskedastic errors and has higher power than existing tests.
New framework for robust hypothesis testing using Sinkhorn uncertainty sets.
problem Non-convex robust hypothesis testing problem.
method Exact mixed-integer exponential conic reformulation and convex approximation.
result Satisfactory testing performance and computational efficiency.
Robust covariance testing requires significantly more samples in contaminated data.
problem Testing the covariance matrix of a high-dimensional Gaussian in the presence of contamination.
method We study the problem in the Huber's contamination model, distinguishing between the identity matrix and matrices far from it in Frobenius norm.
result The sample complexity of covariance testing increases dramatically to Ω(d2) in the contaminated setting. New method tests tree models without causing computational pressure.
problem Incompatibility of adversarial robustness testing with tree ensembles.
method Smooths tree ensembles with sigmoid functions and uses gradient descent.
result Successfully reveals adversarial vulnerability of tree ensemble models.
Robust testing of sparse signals in corrupted data.
problem Testing the norm of high-dimensional sparse signals in the presence of arbitrary corruption.
method Two observation models: i.i.d. samples from N(θ,Id) and sparse linear regression model. result The robust testing requires significantly more samples than non-robust testing.
Quantum classification robustness improved via quantum hypothesis testing.
problem Vulnerability of quantum classification algorithms to input perturbations.
method Formalized link between quantum hypothesis testing and robustness, developed practical protocols.
result Tight robustness condition independent of noise source (natural or adversarial).
Paper extends multivariate rank tests for robust subspace detection.
problem Testing distributional similarity in multivariate data.
method Soft and subspace robust multivariate rank tests based on entropy regularized optimal transport.
result Trade-off between detection power and false alarm rate via projections.
DART2 enhances multiple testing by leveraging ancillary information robustly.
problem Enhancing multiple testing power with uncertain ancillary information.
method Distance-assisted multiple testing procedure (DART2) that handles both helpful and misleading ancillary information.
result DART2 asymptotically controls FDR and improves power when ancillary information is helpful, maintaining FDR and power otherwise.
We propose a semiparametric test to evaluate (i) whether different instruments induce subpopulations of compliers with the same observable characteristics on average, and (ii) whether compliers have observable characteristics that are the same as the full population on average. The test is a flexible robustness check f…
New test for binary treatment effects using kernel methods.
problem Testing distributional effects of binary treatments.
method Kernel-based doubly-robust test, avoiding permutations.
result Valid type-I error with computational efficiency.
New gossip algorithms improve robustness of rank-based statistics in decentralized systems.
problem Ensuring robustness in decentralized AI and edge intelligence systems, especially in the presence of corrupted or adversarial data.
method Developed asynchronous gossip algorithms for computing rank-based statistics.
result First convergence rate bound for asynchronous gossip-based rank estimation.
New tests for distributional causal effects using improved kernel estimators.
problem Testing for higher-order moments and multidimensional outcomes affected by treatment.
method Improved kernel estimators based on doubly robust mean embeddings.
result New permutation-based tests for distributional causal effects with improved convergence rates.
Plug-in robust NPE method adapts summaries independently of pretrained NPE.
problem Misspecification of neural posterior estimators under test data distribution.
method Minimum-distance summaries using maximum mean discrepancy (MMD).
result Substantial robustness gains with minimal additional overhead.
Unified framework for robust A/B testing under model misspecification.
problem Improving sample efficiency in A/B testing with model misspecification.
method Unified framework for contextual bandit and dynamic settings, proving worst-case mean squared error bounds.
result Empirically validated approach using synthetic and real-world datasets.
As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the po…
Proposes MRO to achieve uniformly low regret in distributionally robust learning.
problem Learning under unknown test distributions (distribution shift).
method Minimax Regret Optimization (MRO) for robust machine learning.
result MRO achieves uniformly low regret across all test distributions.
The paper develops robust tests for detecting independence in synchronous stochastic systems with finite sample guarantees.
problem Detecting independence in synchronous stochastic systems with finite sample guarantees.
method Combines confidence region estimates with permutation tests and dependence measures to detect nonlinear dependence.
result Consistent hypothesis tests for detecting independence under mild assumptions.
Estimates and tests treatment effects on entire outcome distributions.
problem Treatment effects on entire outcome distributions, not just averages.
method Proposes a novel estimand and doubly robust estimator, develops a test.
result First test with provably valid type 1 error guarantees in this setting.
Develops robust learning methods for datasets with sub-populations.
problem Robust performance and generalization to unseen testing populations in datasets with sub-populations.
method Min-max-regret (MMR) formulation for distribution-free robust hierarchical model.
result Empirical MMR enjoys regret guarantees on training and unseen testing populations.
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.
Study on adversarial robustness in neural networks across initialization and training phases.
problem Understanding adversarial robustness in neural networks during different learning stages.
method Analyzes adversarial robustness in various scenarios of over-parameterized networks with quadratic targets and infinite samples.
result Robustness can worsen when test error improves, and vice versa, revealing new tradeoffs.
Adversarial robust learning improved for transductive setting.
problem Adversarial robust learning in transductive setting.
method Simple transductive learner for bounded VC dimension classes.
result Robust error rate linear in VC dimension, adaptive to perturbation complexity.
Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic robustness property is still lack of thorough investigation. This work aims to qualitat…
This paper improves conformal prediction to be robust to perturbations.
problem Ensuring robustness of conformal prediction to natural and adversarial perturbations.
method Probabilistically robust conformal prediction (PRCP) and its adaptive version (aPRCP).
result aPRCP achieves better trade-offs between nominal performance and robustness.
CPME embeds counterfactual outcomes in RKHS for flexible policy evaluation.
problem Estimating counterfactual policy outcomes for decision-making.
method Counterfactual Policy Mean Embedding (CPME) framework in RKHS, plug-in and doubly robust estimators, kernel test statistic.
result Doubly robust estimator improves convergence rates and asymptotic normality.
CP improves robustness against distribution shift using physics-informed structural causal models.
problem Uncertainty in machine learning predictions under distributional shift.
method Physics-informed structural causal model (PI-SCM) to upper bound coverage difference.
result PI-SCM improves coverage robustness across confidence levels and test domains.
New measure assesses neural network models' functional similarity.
problem Measuring functional similarity between similar-performing neural networks.
method Robust nonparametric hypothesis testing framework.
result Proposed measure assesses neural networks' functional similarity.
The problem of adversarial robustness has been studied extensively for neural networks. However, for boosted decision trees and decision stumps there are almost no results, even though they are widely used in practice (e.g. XGBoost) due to their accuracy, interpretability, and efficiency. We show in this paper that for…
Trade-off found between privacy and robustness in machine learning models.
problem Balancing privacy and robustness in machine learning models.
method Empirical analysis of trade-offs between robust and private models.
result Privacy and robustness are not always mutually exclusive.
New test for conditional independence using GNNs avoids estimating conditional distributions.
problem Testing conditional independence of X and Y given Z. method Proposes a non-parametric testing procedure using GNNs to sample from marginal conditional distributions.
result Test statistic is doubly robust against GNN approximation errors.
New method learns models to adapt to domain shifts at test time.
problem Learning models robust to distribution shifts in practical applications.
method Adaptive Risk Minimization (ARM) framework.
result Performance gains of 1-4% on image classification problems.
It has been shown that neural network classifiers are not robust. This raises concerns about their usage in safety-critical systems. We propose in this paper a regularization scheme for ReLU networks which provably improves the robustness of the classifier by maximizing the linear regions of the classifier as well as t…
Proposes DR-ME test for interpretable distributional treatment effects.
problem Detects invisible differences in treatment effects on distributional outcomes.
method Semiparametrically efficient finite-location test using kernel witnesses and orthogonal features.
result DR-ME reveals causal-discrepancy coordinates and has noncentral chi-square local power.
A new, fast kernel test for large data.
problem Efficient kernel two-sample tests for high-dimensional, large-scale data.
method A new kernel-based test that is computationally efficient and robust to high dimensions.
result The new test performs well across various alternatives and dimensions.
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.
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…
Deep neural networks (DNN) are increasingly applied in safety-critical systems, e.g., for face recognition, autonomous car control and malware detection. It is also shown that DNNs are subject to attacks such as adversarial perturbation and thus must be properly tested. Many coverage criteria for DNN since have been pr…
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized smoothing over arbitrary functions, and we leverage this novel characterization t…
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and …
Framework for efficient statistical estimation with privacy guarantees.
problem Statistical estimation problems with differential privacy constraints.
method High-dimensional Propose-Test-Release (HPTR) framework combining exponential mechanism, robust statistics, and resilience.
result Near-optimal utility guarantees and tight local sensitivity bounds for various statistical problems.
A new test for volatility in clustered time series data, robust to distributional assumptions.
problem Volatility issues in clustered multiple time series data, especially in stock market indicators.
method Bootstrap method for multiple time series, accounting for contagion effect.
result The test is correctly sized and powerful, especially for stationary mean and contained volatility in fewer clusters.
New framework learns sufficient invariant features robustly across distribution shifts.
problem Learning robust models under distribution shifts between training and test datasets.
method Sufficient Invariant Learning (SIL) framework and Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO) algorithm.
result Empirical evaluations confirm ASGDRO's robustness against distribution shifts.