We propose a supervised anomaly detection method based on neural density estimators, where the negative log likelihood is used for the anomaly score. Density estimators have been widely used for unsupervised anomaly detection. By the recent advance of deep learning, the density estimation performance has been greatly i…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “density anomalies”
Study identifies high-density anomalies in normal data regions.
problem Detecting anomalies in normal data regions.
method Introduces non-parametric algorithmic frameworks for unsupervised detection.
result IPP framework yields the best detection results.
InQMAD detects anomalies in streaming data using quantum measurements and density matrices.
problem Detecting anomalies in streaming data with challenges like conceptual drift and continuous learning.
method Incremental anomaly detection based on random Fourier features and quantum measurements.
result InQMAD outperforms 12 state-of-the-art methods in a systematic evaluation.
EagleEye detects localized density anomalies in multivariate data.
problem Identifying signal events, regime changes, or model mismatch in scientific data.
method EagleEye pinpoints local over- and under-densities by assigning anomaly scores based on binary membership sequences and binomial null models.
result EagleEye can detect genuine local anomalies and estimate background purity.
Research shows deep generative models' likelihoods are unreliable for anomaly detection.
problem Anomaly detection using deep generative models' likelihoods is unreliable.
method Examined the behavior of distribution densities through reparametrization.
result The likelihoods used for anomaly detection rely on strong and implicit hypotheses.
ANODE uses neural density estimation for anomaly detection in physics.
problem Detecting localized anomalies in signal regions with limited background information.
method Estimate data and background densities, construct likelihood ratio, and enhance significance.
result ANODE enhances dijet bump hunt significance by up to 7x with 10% background accuracy.
Paper introduces a new anomaly detection framework combining density estimation and deep learning.
problem Detecting anomalies in data with varying dimensions.
method Two versions: shallow approach using adaptive Fourier features and density matrices; deep approach using autoencoder.
result Both methods achieve comparable or superior performance compared to state-of-the-art methods.
GANF uses normalizing flows to detect anomalies in multiple time series.
problem Detecting anomalies in multiple time series with interdependencies.
method Bayesian network integration with normalizing flows for unsupervised anomaly detection.
result GANF effectively detects anomalies and identifies distribution drift in time series data.
Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Soundseess.AS
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One problem with this approach is that the anomaly score of rare-normal sounds becomes hig…
A new method for anomaly detection using random subspaces and Gaussian mixture models.
problem Anomaly detection in high-dimensional data.
method Statistical estimation of probability density using random subspaces combined with geometric averaging.
result The method achieves competitive AUC scores and is interpretable.
We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These al…
The index theorem connects anomalies on a domain wall to global integrals.
problem Relating anomalies on a domain wall to global integrals.
method Formulated and proved an analog of the Atiyah-Patodi-Singer theorem.
result The index is expressed through global chiral and parity anomalies.
A new method detects anomalies in trajectory data using normalizing flows.
problem Detecting anomalous patterns in high-dimensional, varying-length spatial data.
method Probability density estimation via normalizing flows for each trajectory segment, aggregating likelihoods.
result The proposed method, GRADINGS, effectively identifies anomalies in real-world trajectory data.
New algorithm detects anomalies by forcing samples to displace mass in low-density regions.
problem Detecting anomalies in datasets.
method Mass Repulsing Optimal Transport (MROT) approach.
result Our algorithm improves anomaly detection over existing methods.
GBOC detects anomalies in time series data using granular-ball vectors.
problem Challenges in modeling normal behavior in dynamic, nonlinear time series data.
method Granular-ball Vector Data Description (GVDD) and Granular-ball One-Class Network (GBOC).
result GBOC improves anomaly detection in time series data.
Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detectioncs.LG
LGKDE learns graph density using neural networks and perturbations.
problem Graph density estimation challenges in capturing structural patterns and semantic variations.
method LGKDE uses graph neural networks to represent graphs as discrete distributions and learns graph metrics via maximum mean discrepancy.
result LGKDE outperforms state-of-the-art baselines in graph anomaly detection.
Anomalies (unusual patterns) in time-series data give essential, and often actionable information in critical situations. Examples can be found in such fields as healthcare, intrusion detection, finance, security and flight safety. In this paper we propose new conformalized density- and distance-based anomaly detection…
Proposes differentially private normalizing flows for privacy-preserving density estimation.
problem Privacy concerns in density estimation models when individuals are directly associated with the training data.
method Uses normalizing flow models with explicit differential privacy guarantees.
result Substantially outperforms previous state-of-the-art approaches in privacy-preserving density estimation.
Paper uses DBSCAN variation to detect ship anomalies.
problem Detecting anomalous ship behavior.
method Variation of DBSCAN algorithm applied to AIS data.
result Alternative anomaly metric is more statistically informative.
Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the anomalies are. By contrast, active learning provides the necessary priors through approp…
Detecting anomalous activity in human mobility data has a number of applications including road hazard sensing, telematic based insurance, and fraud detection in taxi services and ride sharing. In this paper we address two challenges that arise in the study of anomalous human trajectories: 1) a lack of ground truth dat…
New method estimates densities using Sobolev regularization, outperforming existing algorithms.
problem Non-parametric density estimation with clear inductive bias.
method Regularizes Sobolev norm of density, approximates kernel via sampling, uses natural gradients for optimization.
result Method ranks second best on ADBench anomaly detection benchmark.
A new anomaly detection method using partial identification.
problem Detecting anomalies in large datasets.
method Partial Identification framework and PIDScore geometric anomaly measure.
result PIDForest outperforms other methods in anomaly detection.
Detects domain shifts in datasets using interpretable feature subspaces.
problem Detecting subtle differences in dataset probability distributions.
method Localised density anomaly detection in high-dimensional feature spaces.
result Extracts interpretable feature subspaces for domain shifts.
GBHT uses gradient boosting for density estimation with theoretical guarantees.
problem Density estimation for unsupervised learning.
method Gradient Boosting Histogram Transform (GBHT) with Negative Log Likelihood loss.
result GBHT achieves faster convergence rates and better performance than base learners in density estimation.
We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their draw…
A new method for anomaly detection adapts to local non-stationarity in low-data regimes.
problem Adapting conformal anomaly detection to handle distribution shifts in real-world data.
method Proposes a continuous inference relaxation using continuous weighted kernel density estimation to decouple local adaptation from tail resolution.
result Restores detection capabilities and statistical power in low-data regimes while maintaining valid error control.
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-…
A framework combines unsupervised and semi-supervised AD using synthetic anomalies.
problem Improving anomaly detection in both unsupervised and semi-supervised settings.
method Proposes a new framework that uses both known and synthetic anomalies for training.
result Synthetic anomalies improve anomaly modeling in low-density regions and provide optimal convergence guarantees.
Study post-hoc Learning to Defer using density-ratio losses.
problem Optimizing decision-making between models and experts.
method Density-ratio losses for post-hoc L2D scorers, derived from class-probability estimation.
result The approach recovers known results and introduces new connections to expert comparison and anomaly detection.
Proposes a method to prevent overfitting in deep DRE models.
problem Overfitting in deep DRE models using empirical Bregman divergence.
method Introduces a non-negative correction for empirical Bregman divergence.
result The proposed method mitigates train-loss hacking and improves performance.
A new method for detecting anomalies in large, high-dimensional data streams using probabilistic forest models.
problem Challenges in detecting anomalies in large, high-dimensional data.
method Probabilistic Mondrian Pólya Forests for summarizing data and estimating underlying probability density.
result State-of-the-art performance with interpretable anomaly scores.
Paper proposes anomaly detection using Eigentraces and one-class classification.
problem Detect anomalies in system call trace data for Linux OS.
method One-class classification with Eigentraces feature extraction, Radial Basis Function neural network, and Random Forest.
result High performance in detecting anomalies and normal activities.
We propose a non-parametric anomaly detection algorithm for high dimensional data. We score each datapoint by its average -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…
We propose a non-parametric anomaly detection algorithm for high dimensional data. We first rank scores derived from nearest neighbor graphs on -point nominal training data. 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…
We compute persistent homology using an intrinsic metric derived from density.
problem Estimating topological features from high-dimensional data.
method Density-based metric learning for persistent homology.
result Persistent homology converges to intrinsic manifold metric.
Standard methods for anomaly detection assume that all features are observed at both learning time and prediction time. Such methods cannot process data containing missing values. This paper studies five strategies for handling missing values in test queries: (a) mean imputation, (b) MAP imputation, (c) reduction (redu…
TailGAN uses GANs to detect anomalies near data distribution tails.
problem Anomaly detection near data distribution tails with current GAN limitations.
method TailGAN leverages GANs with maximum entropy regularization to generate and detect anomalies near data distribution tails.
result TailGAN achieves competitive performance on various datasets compared to existing methods.
BDSG generates samples on distribution boundaries, improving anomaly detection.
problem Difficulty in capturing multimodal supports and approximating distribution tails.
method Invertible Residual Network (IResNet) and Residual Flow (ResFlow) for density estimation; compound loss function for boundary samples.
result Competitive performance on synthetic and multimodal data compared to existing methods.
OneFlow detects anomalies by finding a minimal volume region, outperforming other methods.
problem Anomaly detection in data with complex outlier structures.
method Flow-based one-class classifier that uses a minimal volume region to define outliers.
result OneFlow outperforms other methods in real-world anomaly detection tasks.
Anomaly detection aims to distinguish observations that are rare and different from the majority. While most existing algorithms assume that instances are i.i.d., in many practical scenarios, links describing instance-to-instance dependencies and interactions are available. Such systems are called attributed networks. …
Challenge uses unsupervised learning to detect new physics signals at LHC.
problem Detecting new physics signals at the LHC using unsupervised machine learning.
method Developed and evaluated anomaly detection algorithms on a large dataset.
result Benchmark dataset of >1 Billion simulated LHC events for future studies.
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art anomaly scores are still based on the reconstruction error, which lacks in two e…
We introduce a new unsupervised anomaly detection ensemble called SPI which can harness privileged information - data available only for training examples but not for (future) test examples. Our ideas build on the Learning Using Privileged Information (LUPI) paradigm pioneered by Vapnik et al. [19,17], which we extend …
We propose one-class support measure machines (OCSMMs) for group anomaly detection which aims at recognizing anomalous aggregate behaviors of data points. The OCSMMs generalize well-known one-class support vector machines (OCSVMs) to a space of probability measures. By formulating the problem as quantile estimation on …
We propose one-class support measure machines (OCSMMs) for group anomaly detection which aims at recognizing anomalous aggregate behaviors of data points. The OCSMMs generalize well-known one-class support vector machines (OCSVMs) to a space of probability measures. By formulating the problem as quantile estimation on …
SPTN uses invertible transformations to improve sum-product networks.
problem Improving inference efficiency and tractability in sum-product networks.
method Integrates invertible transformations into sum-product networks (SPNs).
result SPTNs with Gaussian leaves and affine transformations are as tractable as SPNs.
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.