New method detects hidden market predictability despite anomalies.
problem Inference issues in predictive regressions with small violations.
method Novel testing framework resistant to violations of ideal assumptions.
result Large improvements in robust evidence of market predictability.
Detects anomalous inputs in neural networks using subset scanning.
problem Detecting adversarial noise and out-of-distribution samples in neural networks.
method Subset scanning applied to neural network activations using non-parametric scan statistics.
result Identifies the most anomalous subset of node activations in neural networks.
Paper proposes a method to detect unknown anomalous sounds without training data using deep learning and Neyman-Pearson lemma.
problem Unsupervised detection of unknown anomalous sounds in audio data.
method Uses an autoencoder to minimize reconstruction error of normal sounds and Neyman-Pearson lemma to maximize true positive rate under low false positive rate conditions.
result The proposed method improves performance measures of unsupervised anomaly detection in audio data under low false positive rate conditions.
Paper investigates preserving anomalous subgroups in anonymized datasets.
problem Preserving anomalous subgroups in machine learning transformed data.
method Trained a binary classifier to discover anomalous subgroups, then used variational autoencoder (VAE) to anonymize data.
result Synthesized datasets preserved high subgroup differentiation as in original data.
New method explains anomalies in multivariate time series data.
problem Understanding and explaining anomalies in multivariate time series data.
method Counterfactual reasoning applied to MDI-detected anomalous intervals.
result Our method accurately identifies and explains anomalies in various extreme events.
New algorithms detect anomalies in processes with minimal delay.
problem Sequentially selecting and observing processes to identify anomalies.
method Developed centralized and decentralized anomaly detection algorithms using reinforcement learning.
result Minimizes delay in decision making while identifying anomalies accurately.
Anomalous diffusion in SGD reveals interactions between hyperparameters and Hessian.
problem Understanding the limiting dynamics of SGD in deep neural networks.
method Continuous-time model of SGD as an underdamped Langevin equation, derived for linear regression.
result Anomalous diffusion is explained by modified loss and probability currents in phase space.
Most real-world networks exhibit community structure, a phenomenon characterized by existence of node clusters whose intra-edge connectivity is stronger than edge connectivities between nodes belonging to different clusters. In addition to facilitating a better understanding of network behavior, community detection fin…
Anomalous diffusions explain market behavior of implied volatility better than standard models.
problem Reconciling market behavior with standard financial models.
method Analyzed continuous-time random walks with power-law distributed innovation times.
result Anomalous diffusions provide a more consistent fit for implied volatility.
A wide variety of application domains are concerned with data consisting of entities and their relationships or connections, formally represented as graphs. Within these diverse application areas, a common problem of interest is the detection of a subset of entities whose connectivity is anomalous with respect to the r…
Experimental fractal landscape dynamics observed in emulsions.
problem Understanding anomalous motions in soft glassy materials.
method Quantitative analysis of oil droplet trajectories in dense emulsions.
result Experimental fractal geometry matches computational model of soft glassy dynamics.
Special issue on understanding physical processes from unusual diffusion patterns.
problem Understanding physical processes from anomalous diffusion data.
method Not explicitly described in the abstract, but likely involves analysis of data from the Anomalous Diffusion Challenge.
result Not explicitly stated, but likely includes analysis of physical processes from anomalous diffusion data.
ELM combines machine learning and feature engineering for anomalous diffusion detection.
problem Quantitative characterization of anomalous diffusion from single trajectories.
method Extreme Learning Machine (ELM) combined with feature engineering.
result ELM achieves satisfactory performance in AnDi challenge tasks.
Volatility of intra-day stock market indices computed at various time horizons exhibits a scaling behaviour that differs from what would be expected from fractional Brownian motion (fBm). We investigate this anomalous scaling by using empirical mode decomposition (EMD), a method which separates time series into a set o…
Analyzed Bitcoin market index volatility changes over two distinct periods using anomalous diffusion and multifractal analysis.
problem Characterizing volatility changes in Bitcoin market index over two distinct periods.
method Analyzed high-frequency Bitcoin data from 2019 to 2022, using anomalous diffusion and multifractal analysis.
result Volatility changes from subdiffusion to weak superdiffusion over time, with multifractal and self-similar properties.
Paper detects anomalous edges in social networks using edge exchangeability.
problem Detecting anomalous edges in directed social networks.
method Exploits edge exchangeability and uses conformal prediction theory.
result Proposed anomaly detector has a guaranteed upper bound for false positives.
Tests detect anomalous intervals over networks with asymptotically zero error.
problem Detect anomalous intervals over networks with unknown distributions.
method Kernel-based maximum mean discrepancy tests in RKHS.
result Tests are order-level and nearly optimal for minimum and maximum sizes of anomalous intervals.
Study examines extreme and erratic cryptocurrency behaviour during COVID-19.
problem Analyse extreme and erratic cryptocurrency behaviour during the pandemic.
method Analyze distribution extremities and structural breaks in 51 cryptocurrencies.
result Identify cryptocurrencies with most irregular extreme and erratic behaviour.
Paper introduces kernel methods for detecting anomalous changes in remote sensing imagery.
problem Detecting anomalous changes in remote sensing imagery.
method Nonlinear extension of Gaussian and elliptically contoured distribution algorithms using reproducing kernel Hilbert space.
result Improved detection accuracy and reduced false-alarm rates compared to linear formulations.
Paper introduces ToyADMOS dataset for detecting anomalous machine sounds.
problem Lack of large-scale datasets for ADMOS anomaly detection.
method Collected anomalous sounds of miniature machines by deliberate damage.
result Released dataset includes over 180 hours of normal and 4,000 anomalous sounds.
DCASE 2021 ASD task tackles domain-shifted anomalous sound detection.
problem Detecting unknown anomalous sounds under domain-shifted conditions.
method Ensemble of outlier exposure and inlier modeling detectors, feature learning from machine identification.
result Two types of remarkable approaches were adopted by top teams.
Detects anomalous patterns in non-independent data streams.
problem Low detection power for subtle, emerging irregularities in non-iid data.
method Combines Gaussian processes with subset scanning techniques.
result Powerful, interpretable methods for anomalous pattern detection.
The paper explores anomalous subvarieties in hyperbolic 3-manifolds and their geometric implications.
problem Understanding anomalous subvarieties in holonomy varieties of hyperbolic 3-manifolds.
method Analyzing the structure of anomalous subvarieties and their relation to geometric properties of hyperbolic 3-manifolds.
result Maximal anomalous subvarieties of holonomy varieties correspond to specific geometric configurations of cusps in hyperbolic 3-manifolds.
Detects anomalies and locates their causes in large, high-dimensional data.
problem Locating hidden issues in complex systems with high-dimensional data.
method Copula-based model for multivariate probability distributions.
result Can identify and localize anomalies in large, high-dimensional data.
We study the generating functional, the adiabatic curvature and the adiabatic phase for the integer quantum Hall effect (QHE) on a compact Riemann surface. For the generating functional we derive its asymptotic expansion for the large flux of the magnetic field, i.e., for the large degree k of the positive Hermitian …
The electricity market is a very peculiar market due to the large variety of phenomena that can affect the spot price. However, this market still shows many typical features of other speculative (commodity) markets like, for instance, data clustering and mean reversion. We apply the diffusion entropy analysis (DEA) to …
Detects anomalous behavior in social media users by analyzing content and connections.
problem Identifying disruptive patterns in user behavior on social media platforms.
method Joint representation learning of content and connection to detect anomalous behavior.
result Observed densely connected users engaging in local politics and exhibiting troll-like behavior.
The nonparametric problem of detecting existence of an anomalous interval over a one dimensional line network is studied. Nodes corresponding to an anomalous interval (if exists) receive samples generated by a distribution q, which is different from the distribution p that generates samples for other nodes. If anomalou…
Paper discusses ASD challenge for machine condition monitoring.
problem Detecting unknown anomalous sounds without labeled data.
method Design and evaluation of a large-scale ASD dataset, novel approaches.
result Several novel approaches developed, evaluation results analyzed.
Bi-Mamba model predicts diffusion coefficients and exponents from short data.
problem Characterizing anomalous diffusion in complex systems.
method Bidirectional state-space deep learning architecture.
result Efficient inference of diffusion coefficient and exponent from short trajectories.
Anomalous scaling explained by Joseph, Noah, and Moses effects.
problem Understanding and quantifying anomalous scaling in stochastic processes.
method Defined and measured scaling exponents for Joseph, Noah, and Moses effects.
result Intraday financial data shows anomalous scaling due to Moses effect.
Study financial markets using synchronization measures and clustering algorithms.
problem Analyze high-frequency trading dynamics and market states.
method Ordinal pattern series, information-theoretic synchronization measure, clustering algorithms, Markov model.
result Identify two coherent seasons of centralized and decentralized synchronicity.
RCGAN improves anomaly detection by better recognizing anomalous samples.
problem Previous methods fail to correctly detect anomalous data.
method RCGAN uses adversarial training with a new loss function and penalty distribution.
result RCGAN outperforms state-of-the-art methods on various datasets.
We present a systematic study of various statistical characteristics of high-frequency returns from the foreign exchange market. This study is based on six exchange rates forming two triangles: EUR-GBP-USD and GBP-CHF-JPY. It is shown that the exchange rate return fluctuations for all the pairs considered are well desc…
Simulates financial market orders using anomalous diffusion models.
problem Anomalous diffusion in financial market order dynamics.
method Discrete Time Random Walk with Sibuya waiting times, non-uniform sampling, and cubic spline interpolation.
result Demonstrates price impact for different forcing functions and model parameters.
Detects audio adversarial examples using anomalous pattern detection.
problem Identifies adversarial audio attacks in deep neural networks.
method Applies anomalous pattern detection in activation space of audio models.
result Can detect adversarial examples with up to 0.98 AUC, no degradation on benign samples.
HYPA-DBGNN detects anomalous sequential patterns in temporal graphs.
problem Modeling temporal patterns in dynamic graphs, especially considering deviations from random shuffling.
method Two-step approach combining null model inference and neural message passing.
result HYPA-DBGNN outperforms baseline methods in static node classification tasks.
Two machine learning models detect anomalies in ER claims, saving up to 40% in improper payments.
problem Improper health insurance payments from fraud and upcoding.
method Two machine learning models: an upcoding model based on severity code distributions and a random forest model for claim sorting.
result Random forest model saved 12% to 40% in improper payments compared to a baseline approach.
Paper introduces IAD for detecting anomalous VMMs in cloud without VMM access.
problem Anomalous VMMs in cloud-based environments without direct access.
method IAD: Indirect Anomalous VMMs Detection algorithm using VM resource utilization data.
result IAD algorithm outperforms other methods with an average F1-score of 83.7%.
Unified method detects and localizes anomalous cliques in inhomogeneous networks.
problem Detect and localize anomalous cliques in inhomogeneous networks.
method Unified method based on egonets for detection and localization.
result Unified method can detect and localize anomalous cliques in inhomogeneous networks.
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.
AutoSciDACT detects scientific anomalies in noisy data.
problem Detecting anomalies in large, noisy scientific datasets.
method Contrastive pre-training for low-dimensional data representations, two-sample test using NPLM.
result Strong sensitivity to small anomalies across various scientific domains.
Anomaly detection method separates contextual from behavioral attributes.
problem Detect anomalies in data without labeled examples.
method Uses joint deep variational generative models.
result Robust to anomalous or novel contextual attributes.
This research detects anomalies and predicts traffic using CDR data.
problem Detecting and predicting anomalies in mobile network traffic.
method Utilized CDR data, k-means clustering for anomaly detection, neural network for anomaly-free data, and ARIMA for traffic prediction.
result Anomaly-free data leads to better model generalization and prediction performance.
We propose an algorithm for detecting patterns exhibited by anomalous clusters in high dimensional discrete data. Unlike most anomaly detection (AD) methods, which detect individual anomalies, our proposed method detects groups (clusters) of anomalies; i.e. sets of points which collectively exhibit abnormal patterns. I…
Proposes a novel model-agnostic training procedure for anomaly detection incorporating known anomalies.
problem Challenges of anomaly detection, especially when only a few anomalous samples are available.
method Reformulates one-class classification as a binary classification problem, using pseudo-anomalous samples drawn from a normalizing flow model.
result Demonstrates comparable or superior performance on tasks with variable amounts of known anomalies.
IRT improves algorithm evaluation across datasets.
problem Evaluating the performance of algorithm portfolios.
method Modified IRT framework for evaluating algorithm portfolios across datasets.
result Richer characteristics of algorithm performance are revealed.
Improves anomaly detection in deep learning with an auxiliary dataset of outliers.
problem Detecting anomalous inputs in complex, large-scale deep learning models.
method Outlier Exposure (OE) approach: training anomaly detectors against an auxiliary dataset of outliers.
result Significantly improves detection performance on natural language processing and vision tasks.