Picket guards against corrupted data in machine learning models.
problem Data corruption biases models and invalidates predictions.
method PicketNet detects corrupted data using self-supervised deep learning; flags corrupted queries online.
result Picket consistently protects models from corrupted data during training and deployment.
Study improves image classifier robustness to random p-norm corruptions.
problem Improving robustness of image classifiers to real-world imperceptible corruptions.
method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.
result Training with a combination of p-norm corruptions significantly improves robustness.
CUTS removes corruption from models without clean data, improving utility and security.
problem Removing corruption from models without access to clean training data.
method CUTS uses a proxy set to amplify corruption and subtract it from model weights.
result CUTS recovers a large fraction of lost utility and nearly eliminates attacks with minimal damage.
New algorithm robustly trains deep neural networks under corrupted supervision.
problem Training deep neural networks with corrupted supervision data.
method Unified framework for classification and regression, focusing on collective impact of data points on average gradient.
result Achieves strong guarantees without assuming the type of corruption, robust under various types of corruption.
Conventional sampling techniques fall short of drawing descriptive sketches of the data when the data is grossly corrupted as such corruptions break the low rank structure required for them to perform satisfactorily. In this paper, we present new sampling algorithms which can locate the informative columns in presence …
Binary classification improves with a small fraction of corrupted labels.
problem Binary classification with corrupted labels.
method Established corruption as a form of regularization and computed upper bounds on estimation error.
result Corruption is beneficial only up to a small fraction of the total sample, scaling with the square root of the sample size.
Paper introduces robust deep learning method for handling random data corruption.
problem Random corruption in deep learning data due to limited quality of data.
method Inspired by median-of-means and Le Cam's principle, introduces a new approach.
result Demonstrates the approach performs well in practice and is a promising alternative to standard training methods.
Study linear regression with missing or corrupted data, showing error bounds.
problem Linear regression under missing or corrupted data.
method Information-theoretic lower bounds and efficient algorithms.
result Error bounds match in missing and corruption settings.
Develops a comprehensive theory of corruption in supervised learning.
problem Widespread corruption in data collection affects supervised learning problems.
method Introduces a general theory of corruption using Markov kernels, distinguishing and comparing corruption types.
result Establishes a unified framework for corruption types and develops mitigation strategies.
Study finds corruption negatively impacts firm performance.
problem The impact of corruption on firm performance is examined.
method Cross-sectional data analysis of a large international dataset.
result Corruption negatively affects corporate performance.
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.
New method makes robust estimators work without knowing corruption levels.
problem Robust estimation algorithms struggle with unknown corruption levels.
method Abstracted geometric puzzle solution to universal meta technique.
result Converts any robust estimator to work without corruption bounds.
We introduce a new metric to evaluate corruption robustness of ML classifiers.
problem Evaluating corruption robustness of machine learning classifiers.
method We propose a test data augmentation method using minimal class separation distance to derive a robustness distance ε and a metric MSCR.
result The MSCR metric allows interpretable comparison of classifier robustness on different datasets.
New method generates clean data from corrupted observations.
problem Generating clean data from corrupted observations.
method Iterative update of a transport map using black-box corruption channel access.
result Converges to a self-consistent transport map that effectively inverts the corruption channel.
Study robust estimation under varying corruption probabilities in data.
problem Robust estimation in scenarios with heterogeneous corruption rates.
method Developed estimators for mean and regression under various corruption patterns.
result Optimal estimators can discard corrupted samples beyond a specific threshold.
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using…
Adaptive learning method identifies and corrects corrupted data.
problem Robust learning from corrupted training sets.
method Identifies corrupted and non-corrupted samples with latent Bernoulli variables, formulates as likelihood maximization with marginalized latent variables, solved via variational inference and Expectation-Maximization.
result Improves over state-of-the-art by automatically inferring corruption level with minimal overhead.
Efficiently estimates rotations with corrupted data.
problem Rotation synchronization under high corruption and noise.
method Message passing algorithm with reweighted least squares.
result Superior performance over state-of-the-art methods.
We introduce a comprehensive and statistical framework in a model free setting for a complete treatment of localized data corruptions due to severe noise sources, e.g., an occluder in the case of a visual recording. Within this framework, we propose i) a novel algorithm to efficiently separate, i.e., detect and localiz…
We study a data model in which the data matrix D can be expressed as D = L + S + C, where L is a low rank matrix, S an element-wise sparse matrix and C a matrix whose non-zero columns are outlying data points. To date, robust PCA algorithms have solely considered models with either S or C, but not both. As such, existi…
The paper proposes a method to detect and filter noisy or mislabeled data using pointwise mutual information.
problem Detecting and filtering noisy or mislabeled data in deep learning models.
method A mutual information-based framework quantifying statistical dependencies between inputs and labels.
result The method effectively filters low-quality samples, improving classification accuracy by up to 15%.
Adversarial training improves robustness against common corruptions.
problem Improving robustness of models against common corruptions.
method Adversarial training with ℓ p \ell_p ℓ p perturbation and learned perceptual similarity. result Our approach leads to state-of-the-art performance on common corruptions.
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.
New study shows how adversaries can bias fair machine learning models even with corrupted data.
problem Fairness concerns in machine learning models under data corruption.
method Study of fairness-aware learning algorithms under worst-case data manipulations.
result Natural learning algorithms optimizing for both accuracy and fairness are order-optimal in terms of corruption ratio and protected groups frequencies.
We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measure yields adversary models that capture more realistic corruptions than those used in prior works, and present an information-theoretic analy…
Improved SGD for robust linear and ReLU regression with adversarial corruptions.
problem Robust regression with adversarial corruptions in streaming data.
method Stochastic gradient descent (SGD-exp) with exponentially decaying step size.
result Nearly linear convergence to true parameter with up to 50% Massart corruption rate.
Robustly estimates mean with quantized data and corruption.
problem Mean estimation under quantization and adversarial corruption.
method Constructs multivariate robust estimators in two settings.
result Optimal estimators up to logarithmic factors.
Monotone adversarial corruptions degrade optimal learning algorithms.
problem Optimal learning algorithms' reliance on exchangeability and independence is challenged.
method Introduces a monotone adversarial corruption model where an adversary adds monotone corruptions to a clean dataset.
result Optimal learning algorithms achieve suboptimal expected error on new test points.
Framework learns data manifold and generative model from corrupted data.
problem Learning from corrupted data with latent manifold structures.
method Riemannian AmbientFlow, incorporating normalizing flows and Riemannian Autoencoders.
result Framework recovers underlying data distribution and smooth manifold parametrization.
Proposes a robust IV estimator using optimal transport for corrupted or adversarial data.
problem Lack of robustness in traditional IV estimators for corrupted or adversarial data.
method Integrates data-derivative information through optimal transport to address geometric aspects of data.
result Improves robustness against data corruption and adversarial attacks.
New algorithm for robust density estimation in corrupted data.
problem Density estimation in the presence of adversarial corruption.
method Proposes an algorithm for constructing a density estimator within a star-shaped density class, derived minimax bounds for estimation.
result Obtained minimax upper and lower bounds for density estimation under adversarial corruption.
New algorithm resists corruption in linear contextual bandits.
problem Adversarial corruption in linear contextual bandits.
method Variance-aware algorithm with multi-level partition and adaptive confidence sets.
result Regret bound of i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) ilde{O}(C^2d\sqrt{\sum_{t = 1}^T σ_t^2} + C^2R\sqrt{dT}) i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) . Unified framework SVAM learns GLMs robustly to adversarial label corruption.
problem Learning GLMs under adversarial label corruption.
method SVAM framework based on variance reduction technique.
result Provable model recovery guarantees superior to state-of-the-art.
New algorithm robustly learns from corrupted demonstrations, even with constant fraction of noise.
problem Learning from corrupted demonstrations where a fraction of data is noise or outliers.
method Proposes a novel robust algorithm using a Median-of-Means (MOM) objective.
result Guarantees accurate policy estimation even with constant fraction of outliers, similar to classical methods in expert demonstration settings.
Study interprets neural network generalization and memorization on corrupted data.
problem Understanding when a neural network has memorized corrupted data versus learned the underlying rule.
method Analyzes multi-layer perceptrons and Transformers on modular arithmetic tasks with corrupted labels.
result Regularization methods can force networks to ignore corrupted data, improving accuracy on uncorrupted data.
Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence that was developed for regression diagnostics can be used to detect such corrup…
New algorithm robustly estimates sparse models in high dimensions with corrupted data.
problem Estimating latent variable models with arbitrarily corrupted samples in high dimensional space.
method Trimmed (Gradient) Expectation Maximization with trimming gradients and hard thresholding steps.
result The algorithm converges to near optimal statistical rate geometrically under certain conditions.
New algorithm detects communities even with corrupted data, reaching Kesten-Stigum threshold.
problem Robust community detection in stochastic block model with node corruptions.
method Polynomial-time algorithm using Grothendieck norm of principal submatrices.
result First algorithm to achieve weak recovery at Kesten-Stigum threshold with node corruptions.
The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time. Until now, several important challenges still cannot be handled concurrently: 1) corrupted data e…
We consider a general statistical learning problem where an unknown fraction of the training data is corrupted. We develop a robust learning method that only requires specifying an upper bound on the corrupted data fraction. The method minimizes a risk function defined by a non-parametric distribution with unknown prob…
Paper proposes a self-supervised method to denoise autoregressive signals with heavy-tailed noise.
problem Denoising autoregressive signals corrupted by heavy-tailed noise.
method Self-supervised learning approach without requiring full noise distribution knowledge.
result Strong denoising performance compared to baseline methods, especially for impulsive noise.
Enhances deep networks robustness with data mollification and label smoothing.
problem Improving deep neural networks' robustness against corruptions.
method Coupling data mollification (image noising and blurring) with label smoothing.
result Improved robustness and uncertainty quantification on corrupted image benchmarks.
New method tackles tensor regression with robust Kaczmarz approach.
problem Reconstructing tensor signals from corrupted measurements.
method Quantile-based randomized Kaczmarz method for tensor linear systems.
result Improved convergence and robustness to adversarial corruptions.
Improves tabular data augmentation for contrastive learning.
problem Ineffective augmentation techniques for tabular data.
method Class-conditioned and feature-correlation based augmentation.
result Consistently outperforms conventional corruption methods.
No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formal…
The US Census Bureau corrupts data to protect privacy, but we show how to clean and analyze it effectively.
problem Analyzing Census data with intentional corruption to maintain privacy.
method Formulated a semiparametric model, proposed data cleaning, estimation, and inference procedures.
result Demonstrated that data cleaning can maintain precision and provided theoretical and empirical support.
Novel method solves group synchronization with robust corruption tolerance.
problem Group synchronization with high corruption tolerance.
method Quadratic programming formulation exploiting cycle consistency.
result Global minimum recovers corruption levels under mild conditions.
New estimator reduces kernel mean estimation error.
problem Kernel mean estimation in reproducing kernel Hilbert spaces.
method Corrupt data with known distributions and estimate kernel mean under the corrupted distribution.
result The marginalized kernel mean estimator achieves lower estimation error.