A new model detects and localizes anomalies in multivariate time series data.
problem Anomaly diagnosis in multivariate time series data, especially localization.
method Attention Low-Rank Transformer (ALoRa-T) with low-rank regularization and Attention Low-Rank score.
result The proposed method significantly outperforms state-of-the-art methods in anomaly detection and localization.
We propose a novel non-parametric adaptive anomaly detection algorithm for high dimensional data based on rank-SVM. Data points are first ranked based on scores derived from nearest neighbor graphs on n-point nominal data. We then train a rank-SVM using this ranked data. A test-point is declared as an anomaly at alpha-…
Meta-AAD uses deep reinforcement learning to improve anomaly detection by selecting the most informative instances.
problem High false-positive rate in anomaly detection, especially in high-stake applications.
method Meta-AAD leverages deep reinforcement learning to train a meta-policy for query selection, optimizing the number of discovered anomalies.
result Meta-AAD significantly outperforms state-of-the-art re-ranking strategies and unsupervised baselines on 24 benchmark datasets.
The paper introduces a method to incorporate feedback into tree-based anomaly detection to reduce false positives.
problem Difficulty in human analysts examining high-ranking anomalies due to false positives.
method Incorporates simple binary feedback into tree-based anomaly detectors, focusing on the Isolation Forest algorithm.
result Significantly improves the performance of the Isolation Forest algorithm by reducing false positives.
New algorithm ranks anomalies in high dimensions using EVT.
problem Anomaly detection in high-dimensional data.
method Multivariate Extreme Value Theory (EVT) for sparse representation.
result Sparse representation of multivariate extremes for anomaly ranking.
Anomaly detection algorithm using nearest neighbor graphs and max-margin learning.
problem Anomaly detection in high-dimensional data.
method Rank nearest neighbor scores, train max-margin models to imitate, declare anomalies based on percentile.
result Asymptotically optimal decision region converges to minimum volume level set.
We propose a non-parametric anomaly detection algorithm for high dimensional data. We score each datapoint by its average K-NN distance, and rank them accordingly. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as an anomaly…
Analytic torsion defined for rank 2 distributions on 5-manifolds.
problem Defining and analyzing analytic torsion for rank 2 distributions.
method Proposed an analytic torsion for Rumin complex associated with rank 2 distributions on 5-manifolds, established anomaly formulas, and showed coincidence with Ray-Singer torsion.
result The proposed torsion coincides with Ray-Singer torsion for certain nilmanifolds.
A new method detects and ranks anomalies in cloud computing platforms using multi-view learning.
problem High false-alarm rate in traditional anomaly detection methods.
method Online model using machine learning theory, ELM for efficiency, and multi-view feature fusion.
result Improved accuracy and efficiency in anomaly detection and ranking.
StealthRank subtly boosts LLM rankings without detectable anomalies.
problem Adversarial manipulation of LLM-driven ranking systems.
method Energy-based optimization with Langevin dynamics for stealthy prompt generation.
result StealthRank outperforms existing methods in covertly boosting rankings.
Given the superposition of a low-rank matrix plus the product of a known fat compression matrix times a sparse matrix, the goal of this paper is to establish deterministic conditions under which exact recovery of the low-rank and sparse components becomes possible. This fundamental identifiability issue arises with tra…
CAD detects anomalies and selects prototypes using polyhedron curvature.
problem Anomaly detection and prototype selection in data.
method Curvature Anomaly Detection (CAD) and Kernel CAD approach using polyhedron curvature.
result The proposed methods are effective for anomaly detection and prototype selection.
New method reduces inventory inaccuracies by 10x, saving retailers 4% annually.
problem Inaccurate inventory records cost retailers 4% annually, and manual detection is impractical.
method Proposes a new anomaly detection method for low-rank Poisson matrices using cross-sectional data.
result Our approach reduces anomaly detection costs by up to 10x compared to existing methods.
We find a rank effect in commodity prices that yields higher returns.
problem Understanding the pricing dynamics of commodities over time.
method Nonparametric econometric methods to demonstrate the rank effect as a consequence of stationary relative asset price distribution.
result A portfolio of lower-ranked, lower-priced commodities yields 23% higher annual returns than a portfolio of higher-ranked, higher-priced commodities.
Learning how to rank multivariate unlabeled observations depending on their degree of abnormality/novelty is a crucial problem in a wide range of applications. In practice, it generally consists in building a real valued "scoring" function on the feature space so as to quantify to which extent observations should be co…
Robust PCA detects anomalies and fills gaps in seasonal time series data.
problem Anomaly detection and data imputation in seasonal time series.
method Online robust PCA framework for temporal observations.
result Empirically compared and showed effectiveness in practical situations.
Paper introduces an unsupervised tensor-based anomaly detection method for spatiotemporal data.
problem Challenges in detecting anomalies in spatiotemporal data, especially in urban traffic monitoring and medical imaging.
method Formulates anomaly detection as a regularized robust low-rank + sparse tensor decomposition, incorporating spatiotemporal smoothness and local dependencies.
result Demonstrates improved anomaly detection performance on both synthetic and real data.
Unified model for signed networks separates balance and anomaly effects.
problem Ignoring sign information in signed networks leads to inaccurate analysis.
method Low rank plus sparse matrix decomposition with regularized formulation.
result The model accurately detects communities and anomalies in signed networks.
The paper introduces a new method to rank anomalies in multivariate data.
problem Ranking multivariate unlabeled observations based on their degree of abnormality.
method Formulates the problem as a M-estimation problem using the Mass Volume curve (MV curve).
result Established generalization bounds for the MV curve estimation.
Detects anomalies in product health metrics at eBay for better alerts.
problem Detecting anomalies in unsupervised product health metrics at eBay.
method Developed a Moving Metric Detector (MMD) for anomaly detection and a point-wise ranking model for alert retrieval.
result Improves alert precision and avoids alert spamming in eBay production.
Paper proposes a scoring function for detecting anomalies in large datasets.
problem Detecting outliers in large, feature-rich datasets.
method Binary classification problem with a two-sample linear rank statistic.
result Empirical results show the effectiveness of the proposed scoring function.
BADAC combines Bayesian methods for anomaly detection and classification.
problem Statistical uncertainties in machine learning algorithms, especially for anomaly detection.
method Unified hierarchical Bayesian framework that marginalizes over unknown data values.
result BADAC outperforms standard algorithms in classification and anomaly detection with uncertainties.
A novel one-class classifier fusion method for robust anomaly detection.
problem Fundamental challenges in ensemble-based anomaly detection.
method Locally adaptive learning with dynamic ℓp-norm constraints and interior-point optimization.
result Significantly improved computational efficiency and superior performance across diverse anomaly types.
CCE improves anomaly detection metrics by measuring both confidence and consistency.
problem Existing anomaly detection metrics lack discriminative power, hyperparameter dependency, and robustness to perturbations.
method CCE uses Bayesian estimation to quantify uncertainty and constructs global and event-level confidence and consistency scores.
result CCE demonstrates strict boundedness, robustness, and linear time complexity.
Paper proposes efficient online data thinning for expert analysis.
problem Large-scale streaming data exceeds human analysis capacity.
method Online anomaly detection using dynamic low-rank Gaussian mixture models.
result Proposed method reduces data to unique elements for timely analysis.
A new method QMS22 for semi-supervised anomaly detection outperforms existing methods.
problem Semi-supervised anomaly detection in datasets with overlapping normal and outlier samples.
method QMS22, a classifier that solves a multi-class classification problem involving both training and test sets.
result QMS22 significantly outperforms ISOF and ocSVM in anomaly detection.
New method selects kernel bandwidth for SVDD and OCSVM.
problem Selecting optimal Gaussian kernel bandwidth for SVDD and OCSVM.
method Exploits low-rank representation of kernel matrix to suggest bandwidth.
result Method performs well for both low-dimensional and high-dimensional data.
New study on time series anomaly detection shows overlapping inference improves performance.
problem Heterogeneous evaluation practices and inference procedures in time series anomaly detection.
method Unified training, tuning, and evaluation protocol on TSB-AD benchmark, analyzing overlapping vs. disjoint inference.
result Overlapping inference yields consistent improvements, with average relative gain up to +28%.
Paper tackles anomaly detection in large-scale networks.
problem Inferring network-level anomalies from indirect link measurements.
method Online subspace tracking of Hankelized traffic tensor using Candecomp/PARAFAC decomposition and RLS algorithm for normal flows; outlier detection for abnormal flows.
result Proposed algorithm achieves faster convergence and better anomaly detection performance.
New unsupervised feature selection method for imbalanced datasets.
problem Feature selection challenges in imbalanced multi-class datasets.
method Distance Rank Score using Spearman's Rank Correlation.
result Outperforms existing methods on clustering problems.
Security issues are crucial in a number of machine learning applications, especially in scenarios dealing with human activity rather than natural phenomena (e.g., information ranking, spam detection, malware detection, etc.). It is to be expected in such cases that learning algorithms will have to deal with manipulated…
The paper proves concentration inequalities for two-sample rank processes and applies them to ranking performance criteria.
problem Measuring the performance of ranking statistics between two populations.
method Proves concentration inequalities for two-sample rank processes indexed by VC classes of scoring functions.
result Generalization capacity of empirical maximizers of ranking performance criteria is investigated.
We construct a class of stable SU(5) bundles on an elliptically fibered Calabi-Yau threefold with two sections, a variant of the ordinary Weierstrass fibration, which admits a free involution. The bundles are invariant under the involution, solve the topological constraint imposed by the heterotic anomaly equation and …
We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured by solving a non-linear, low-rank representation problem. We show that this low-…
Detect anomalous regions in spatio-temporal data.
problem Detecting coherent anomalous regions in large spatio-temporal datasets.
method Maximally Divergent Intervals (MDI) framework for unbiased Kullback-Leibler divergence.
result Our method identifies coherent anomalous regions in various data types.
The paper models financial correlation matrices using permutation invariant Gaussian models and predicts market anomalies.
problem Modeling and predicting financial correlation matrices from high-frequency data.
method Constructing permutation invariant Gaussian matrix models with 4 parameters, using graph theory and polynomial functions.
result The permutation invariant Gaussian matrix model predicts the expectation values of cubic and quartic polynomials with strong evidence of fit.
In this paper we present a construction of stable bundles on Calabi-Yau threefolds using the method of bundle extensions. This construction applies to any given Calabi-Yau threefold with h^{1,1}>1. We give examples of stable bundles of rank 2 and 4 constructed out of pure geometric data of the given Calabi-Yau space. A…
Improves anomaly detection with contaminated unlabeled data.
problem Weakness in existing semi-supervised anomaly detection methods when unlabeled data contain anomalies.
method Integrates positive-unlabeled learning with deep anomaly detection models.
result Achieves better detection performance on various datasets.
End-to-end anomaly detection framework using labeled anomalies.
problem Limited deep learning for anomaly detection and inefficiency of existing methods.
method Deviation learning neural network with labeled anomalies and prior probability.
result Significantly better anomaly scoring than state-of-the-art methods.
PReNet detects seen and unseen anomalies using pairwise relations.
problem Detecting unseen anomalies in semi-supervised learning.
method Pairwise Relation prediction Network (PReNet) learns anomaly and normal patterns.
result PReNet significantly outperforms nine competing methods in anomaly detection.
CANARI detects near-anomalies to predict future anomalies proactively.
problem Uncertainty in anomaly detection near distribution boundaries.
method Christoffel-based ANomaly Anticipation for eaRly dIscovery (CANARI) method.
result CANARI outperforms baseline methods in detecting near-anomalies and predicting future anomalies.
Proposes a method for anomaly detection with inexact labels.
problem Handling anomaly detection with inexact labels.
method Trains an anomaly score function using a neural network-based unsupervised method, maximizing the inexact AUC.
result Improves anomaly detection performance with inexact labels and outperforms existing methods.
Detects anomalies relative to typical observations.
problem Common anomaly detection methods fail for frequent anomalies.
method Relative anomaly detection, considering location relative to typical observations.
result Effective for frequent anomalies, computationally feasible, real-time detection.
Deep RL detects anomalies from few labeled examples and large unlabeled data.
problem Anomaly detection with limited labeled data and large unlabeled data.
method Deep reinforcement learning to optimize detection of labeled and unlabeled anomalies.
result Significantly outperforms state-of-the-art methods on 48 real-world datasets.
A new depth function improves multivariate data analysis by considering variability directions.
problem Developing a depth function that respects quantile properties and is affine-invariant.
method Integrating rank-weighted depth with affine-invariance and covariance matrices.
result The AI-IRW depth function provides accurate quantile estimates and is robust to data variability.
A new method assigns anomaly scores to features for better interpretation.
problem Interpreting anomaly scores from feature attributions.
method Proposes a characteristic function to attribute anomaly scores using Shapley value.
result Demonstrates the potential utility of the proposed attribution methods.
Efficient method detects point and collective anomalies in data sequences.
problem Efficiently identifying anomalies in data sequences, especially collective anomalies.
method CAPA: a computationally efficient approach for detecting collective and point anomalies.
result CAPA is consistent at detecting collective anomalies and has close to linear computational cost.
Novel framework monitors cardiac image segmentation models in real-time.
problem Ensuring continuous high model performance and segmentation results in clinics.
method Formulated as anomaly detection, the framework derives surrogate quality measures for segmentation.
result Demonstrated accurate, fast, and scalable quality control monitoring.