Develops a new approach for detecting context-dependent multivariate outliers.
problem Challenges of detecting context-dependent multivariate outliers.
method Transforms conditional detection to unconditional space and uses classifier chain decomposition.
result Methodology successfully identifies outliers in sparse or dense conditions.
New framework detects unusual input-output associations in multivariate data.
problem Detecting conditional outliers in multivariate data.
method Decomposable conditional probabilistic model with component weights.
result Framework successfully identifies multivariate conditional outliers.
Paper proposes a new method for selective inference in robust regression.
problem Statistical inference after removing outliers identified by robust methods.
method Conditional SI using piecewise-linear homotopy continuation.
result Proposed method is applicable to a wide class of robust regression and outlier detection methods.
OutlierTree detects outliers using decision trees and provides explanations.
problem Detecting outliers in data while providing understandable explanations.
method Supervised decision tree splits with 1-d confidence intervals.
result Human-readable explanations for outlier detection.
Identifies root causes of outliers using causal DAGs.
problem Detecting and understanding the causes of anomalies in interrelated variables.
method Formal approach using causal directed acyclic graphs (DAGs), outlier scores, and Shapley values.
result Quantifies the extent of outlier scores attributed to ancestors.
Paper proposes a method to robustly detect and exclude outliers in web-collected datasets for improved classification.
problem Outliers in web-collected datasets pose a significant challenge for robust classification.
method The approach combines Pre-conditioned LASSO and unsupervised transductive diffusion component analysis.
result The method effectively detects and excludes outliers, leading to improved classification performance.
Study improves data quality assessment for structural monitoring data.
problem Ensuring reliability of structural health monitoring data.
method Probabilistic data quality assessment using a conditional diffusion model.
result Significantly improves accuracy of data quality assessment.
This paper bridges outlier-robust estimation in robotics and computer vision with robust statistics.
problem Outlier-robust estimation for geometric perception in robotics and computer vision.
method Adapting and extending robust linear regression and list-decodable regression to non-convex domains and vector-valued measurements.
result Performance guarantees for modern estimation algorithms in the presence of outliers.
A contaminated mixture model detects outliers in multivariate functional data.
problem Detecting abnormal sensor measurements in multivariate functional data.
method A contaminated mixture model that clusters and detects outliers without specifying outlier proportion.
result The model outperforms competitors and correctly detects abnormal behaviors in real data.
Study improves regression models for non-Gaussian noise and outliers using correntropy.
problem Improving regression models for non-Gaussian noise and outliers.
method Introduces mixture of symmetric stable noise and uses correntropy for regression.
result Establishes asymptotic optimal learning rates for correntropy based regression.
The paper introduces localized conformal p-values for conditional testing problems.
problem Addressing conditional testing problems in statistics.
method Localized conformal p-values defined by inverting prediction intervals.
result Proposes procedures for conditional outlier detection and label screening with FDR and FWER control.
The paper finds outliers in large matrices with noisy or missing data.
problem Locating outliers in large, noisy or incomplete matrices.
method Randomized two-step inference framework with sample complexity conditions.
result The proposed methods accurately locate outliers with high probability.
Robustly learns Ising models with corrupted data.
problem Learning Ising models corrupted by a constant fraction of adversarial samples.
method Develops a computationally efficient algorithm for robust learning.
result First near-optimal error guarantees for robust learning of Ising models.
Bayesian method detects outliers and uncertain points in data.
problem Detecting outliers and uncertain points in data using Bayesian methods.
method Generative model of data curation for aleatoric uncertainty, combining with epistemic uncertainty and outlier exposure.
result Principled Bayesian approach outperforms methods using aleatoric or epistemic uncertainty alone.
Paper develops a method to robustly cluster tensors with outliers.
problem Clustering tensors contaminated by outliers or sample-specific corruptions.
method Transformed Tensor Low-Rank Representation (OR-TLRR) method.
result Provably recovers row space of clean data and detects outliers.
Improved clustering with outlier detection using cardinality constraints.
problem Outlier sensitivity and unbalanced clusters in K-means.
method Formulates a joint outlier detection and clustering problem as a mixed-integer linear program (MILP) with cardinality constraints.
result Proves the optimality of solutions under certain conditions.
Paper proposes fast algorithms for detecting outliers in crowdsourced QoE evaluations.
problem Detecting outliers in crowd-sourced QoE evaluations.
method Simple and fast iterative algorithms based on nonconvex optimization.
result The proposed algorithms achieve similar performance to Huber-LASSO but with significantly faster speed.
Paper proposes a matrix optimization model for reliable Euclidean embedding from noisy data.
problem Challenges in Euclidean embedding from noisy observations containing outliers.
method Matrix optimization based embedding model to detect and remove outliers.
result The model provides high accuracy estimators and successfully identifies outliers.
New algorithms robustly estimate mean with near-optimal error rates.
problem Outlier robust mean estimation in high-dimensional data.
method Stability condition and iterative filtering algorithms.
result Optimal error rates with subgaussian rates for robust mean estimation.
New algorithm clusters networks with outliers, achieving exact recovery.
problem Clustering networks with outliers and degree corrections.
method Convex optimization with a penalization term for positive deviations.
result Achieves exact recovery of clusters under mild conditions.
BAE uses boosting to improve autoencoder ensembles for robust outlier detection.
problem Overfitting in autoencoders limits their effectiveness in unsupervised outlier detection.
method Boosting-based Autoencoder Ensemble (BAE) trains autoencoders sequentially with weighted sampling to reduce outliers and inject diversity.
result BAE outperforms state-of-the-art approaches in various outlier detection conditions.
S2D selectively decays large singular values to improve quantization of neural activations.
problem Large activation outliers in transformer models cause accuracy drops during quantization.
method Selective Spectral Decay ( S 2 D S^2D S 2 D ) that surgically regularizes only the largest singular values. result Significantly reduces activation outliers and produces well-conditioned representations.
Mixtures of multivariate contaminated shifted asymmetric Laplace distributions are developed for handling asymmetric clusters in the presence of outliers (also referred to as bad points herein). In addition to the parameters of the related non-contaminated mixture, for each (asymmetric) cluster, our model has one param…
New SMC sampler improves diffusion model sampling efficiency.
problem Sampling generative diffusion models efficiently.
method Constructs correlated observation paths and designs a sampler.
result Improved statistical efficiency, especially under outlier conditions.
Robust estimation under MCC shows near-perfect accuracy even with large outliers.
problem Robustness of maximum correntropy estimation against large outliers.
method Parameter estimation for a simple linear EIV model using maximum correntropy criterion.
result The optimal solution under MCC can be very close to the true value of the unknown parameter even with large outliers.
Suppose a given observation matrix can be decomposed as the sum of a low-rank matrix and a sparse matrix (outliers), and the goal is to recover these individual components from the observed sum. Such additive decompositions have applications in a variety of numerical problems including system identification, latent var…
HSNLD solves robust Hankel recovery efficiently and robustly.
problem Robust Hankel recovery of sparse outliers and missing entries.
method Hankel Structured Newton-Like Descent (HSNLD) algorithm.
result HSNLD achieves linear convergence independent of the condition number.
A robust model handles up to 25% of outliers in time-series data for power flow calculations.
problem Handling outliers in time-series data for accurate power flow calculations.
method Robust data-driven process model with Schweppe-type generalized maximum likelihood estimator and projection statistics for outlier weighting.
result The model can handle up to 25% of outliers in the training data set.
A new method makes Gaussian filters robust to outliers.
problem Outliers in sensor measurements disrupt Gaussian filters.
method Apply a pseudo measurement derived from a feature function.
result The method effectively handles outliers in both linear and nonlinear systems.
Efficient algorithm for conditional linear regression.
problem Building models that accurately predict a specific segment of data.
method Efficient algorithm for identifying a significant segment of the population and its linear regression fit.
result Theoretical analysis and efficient algorithm for conditional linear regression.
Paper improves robust PCA for noisy, outlier, and missing data.
problem Robust PCA with noise, outliers, and missing data.
method Bridging convex and nonconvex optimization.
result Near-optimal statistical accuracy for robust PCA.
ERM and RERM minimize error even with malicious label corruptions.
problem Malicious label corruptions in regression problems.
method Empirical Risk Minimizers (ERM) and Regularized Empirical Risk Minimizers (RERM) under a local Bernstein condition.
result The L 2 L_2 L 2 -error rate is bounded by $r_N + AL |\cO|/N$ under the local Bernstein condition. SubTSBR tackles noisy data for differential equation discovery.
problem Discovering differential equations from noisy or outlier-laden data.
method Subsampling-based threshold sparse Bayesian regression (SubTSBR) with subsampling size and number of subsamples.
result SubTSBR outperforms TSBR in accuracy for differential equation discovery.
KMRCD detects outliers in non-elliptical data using kernel trick.
problem Outlier detection in non-elliptical data.
method KMRCD estimator that uses kernel trick to compute robust covariance matrix in a feature space.
result KMRCD performs well in simulations and real-life data.
Develops a robust GMM estimator for outlier-tolerant inference.
problem Sensitive GMM estimation to outliers in inference problems.
method Robustified GMM estimator with computational efficiency and recovery guarantees.
result First computationally efficient GMM estimator for ε ε ε fraction of adversarial outliers with O ( ε ) O(\sqrtε) O ( ε ) recovery guarantee. Algorithm finds a subspace minimizing distances to inliers with outliers.
problem Finding a k k k -dimensional subspace minimizing distances to inliers with outliers. method Extends dimension reduction techniques and bi-criteria approximations based on sampling.
result Efficient algorithm for multiplicative ( 1 + ε ) (1+ε) ( 1 + ε ) -approximation of optimal solution. Theoretical guarantees for STE, a robust subspace recovery method.
problem Recovering a low-dimensional subspace from corrupted data.
method Subspace-constrained Tyler's estimator (STE) with initialization conditions.
result STE can effectively recover the subspace under certain conditions.
A new algorithm identifies outliers in Gaussian clustering models.
problem Handling outliers in Gaussian model-based clustering.
method OCLUST algorithm removes least plausible points based on subset log-likelihoods until they adhere to a reference distribution.
result OCLUST inherently estimates the number of outliers.
Proposes COIN method for explaining outliers.
problem Lack of interpretation for outlier detection.
method Contextual Outlier INterpretation (COIN) method.
result Demonstrates flexibility and effectiveness compared to existing methods.
Proposes a method to detect and explain outliers using localized logistic regression.
problem Detecting and explaining outliers in high-dimensional data.
method Localized logistic regression for density ratio estimation.
result The method successfully detects important features for outliers and outperforms existing algorithms.
New algorithm identifies outliers in PCA without needing parameters.
problem Robust PCA with unknown outlier fraction and subspace dimension.
method Non-iterative, parameter-free method for structured and unstructured outliers.
result Analytical guarantees and performance comparison with existing methods.
Paper proposes iLPA for solving DC composite optimization problems, with applications to matrix completion with outliers.
problem Solving nonconvex and nonsmooth DC composite optimization problems.
method Inexact linearized proximal algorithm (iLPA) for DC composite optimization problems.
result The iLPA achieves local R-linear convergence rate under the Kurdyka-Łöjasiewicz property.
Paper connects contrastive learning to MI maximization and establishes robust methods for nonlinear ICA and subspace estimation.
problem Understanding and improving unsupervised representation learning and density ratio estimation.
method The paper connects contrastive learning to MI maximization, establishes new recovery conditions for nonlinear ICA, and proposes a practical outlier-robust method for nonlinear subspace estimation.
result The proposed methods can be seen as maximizing MI, performing nonlinear ICA, or estimating nonlinear subspaces, and are robust to outliers.
New method detects outliers in correlated data.
problem Detecting outliers in noisy, correlated datasets.
method Robust regression model that detects outliers during model fitting.
result Outlier detection method achieves better performance.
A novel approach ODAR detects outliers for clustering.
problem Outliers interfere with clustering algorithms, leading to unreliable results.
method Feature transformation to separate outliers and normal objects into distinct clusters.
result ODAR improves clustering accuracy on 7 out of 10 datasets.
A robust Gaussian process model using Huber likelihood for outlier resistance.
problem Outliers in observational data sets affect Gaussian process regression's robustness.
method Proposes a Gaussian process model with Huber likelihood and weights based on projection statistics.
result Demonstrates improved statistical efficiency and robustness to outliers.
New framework detects outliers in non-IID categorical data.
problem Existing outlier detection methods fail in non-IID data.
method Value-value graph-based representation and outlierness propagation.
result Significant improvement in AUC on complex data sets.
Paper proposes methods to make OT robust to outliers.
problem Optimal transport is sensitive to outliers.
method Detect outliers using adversarial training, adjust transport cost based on classifier predictions.
result Outliers are detected and do not affect transport in experiments.