Generative model attacks CNN on MNIST by subtly replacing input patterns.
problem Adversarial attacks on neural networks.
method Generative model that replaces input patterns with generated ones.
result Demonstrated effectiveness on MNIST dataset.
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “subtle patterns”
Machine learning detects drug overdose trends, aiding prevention.
problem Detecting subtle overdose patterns in spatio-temporal data.
method Gaussian Process Subset Scan and Multidimensional Tensor Scan.
result Identifies previously unknown overdose patterns and demographic clusters.
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.
Machine learning detects subtle glucose changes for early diabetes diagnosis.
problem Challenging early-stage diabetes diagnosis due to subtle glucose changes.
method Applied machine learning to synthetic glucose profiles generated by a biophysical model.
result High accuracy (above 85%) in detecting insulin resistance using various neural networks.
Interpersonal relations are fickle, with close friendships often dissolving into enmity. In this work, we explore linguistic cues that presage such transitions by studying dyadic interactions in an online strategy game where players form alliances and break those alliances through betrayal. We characterize friendships …
Coordination and Trajectory Prediction for Vehicle Interactions via Bayesian Generative Modelingcs.RO
System predicts vehicle interactions and trajectories with uncertainty.
problem Predicting future vehicle trajectories with uncertainty.
method Hierarchical Bayesian Generative Modeling with categorized and real-valued coordination variables.
result Categorized coordination better captures multi-modality and generates more diverse samples.
New method predicts AD progression using MEG brain networks.
problem Early diagnosis and prediction of Alzheimer's disease progression.
method MG2G, a deep learning method that maps brain networks into a latent space.
result MG2G detects subtle brain connectivity patterns and predicts AD progression.
CNNs overinterpret inputs, leading to high accuracy without meaningful features.
problem High accuracy in image classifiers can mask subtle model failures.
method Batched Gradient SIS method for discovering sufficient input subsets.
result Overinterpretation allows models to make confident predictions with masked input features.
Radiomics identifies subtle cardiac changes in hypertension.
problem Subtle cardiac alterations in hypertension not captured by conventional imaging.
method Combines feature selection and machine learning for identifying structural and tissue changes.
result Radiomics model detects changes beyond conventional imaging.
In this paper, we propose a new algorithm for exploratory projection pursuit. The basis of the algorithm is the insight that previous approaches used fairly narrow definitions of interestingness / non interestingness. We argue that allowing these definitions to depend on the problem / data at hand is a more natural app…
LSTM networks improve stock price prediction accuracy.
problem Enhancing stock price forecasting accuracy.
method LSTM networks with hyperparameter tuning and feature selection.
result 53% improvement in predictive accuracy.
Tensor-based methods improve mid-price prediction in high-frequency financial data.
problem Predicting price changes in high-frequency financial data.
method Multilinear tensor-based learning algorithms for mid-price prediction.
result Tensor-based models outperform vector-based approaches in mid-price prediction.
The paper disproves a conjecture about satellite maps not inducing homomorphisms.
problem Satellite maps and their impact on knot concordance groups.
method Casson-Gordon signatures and -solvable filtration analysis.
result Examples of satellite maps that act like homomorphisms but do not induce them.
Model predicts option movements using residual transactions for better market timing.
problem Predicting option movements using standard metrics like open interest and trading volume.
method Analyzes residual transactions, integrates machine learning and regression techniques.
result Identifies early indicators of market trends for better option price forecasting.
Agent optimizes risky asset trading times based on Prospect Theory.
problem Optimizing speculative trading times with transaction costs.
method Formulated as a sequential optimal stopping problem, characterized the solution.
result Trading patterns influenced by preference and market friction.
Multifractal analysis reveals complex patterns in financial markets.
problem Understanding the complex nonlinear nature of financial time series.
method Multifractal analysis methods and models applied to financial markets.
result Multifractality is ubiquitously observed in financial markets.
Big Data bring new opportunities to modern society and challenges to data scientists. On one hand, Big Data hold great promises for discovering subtle population patterns and heterogeneities that are not possible with small-scale data. On the other hand, the massive sample size and high dimensionality of Big Data intro…
Researchers provide a simple topological method for Burau representations of loop braid groups.
problem Constructing Burau representations of loop braid groups.
method Simple topological construction of the Burau representations.
result One of the representations is more subtle and topologically natural but not easily combinatorially obvious.
The subtle interplay between local and global charges for topological semimetals exactly parallels that for singular vector fields. Part of this story is the relationship between cohomological semimetal invariants, Euler structures, and ambiguities in the torsion of manifolds. Dually, a topological semimetal can be rep…
Study develops algorithm to detect subtle respiratory events from PSG recordings.
problem Detecting non-apneic and non-hypopneic arousals in polysomnography recordings.
method Bidirectional LSTM classifier with 465 multi-domain features.
result 0.50 AUPRC on hidden test dataset, tied for second-best score in 2018 PhysioNet challenge.
t-NEB clusters high-dimensional data hierarchically with density paths.
problem Hierarchical clustering struggles with high-dimensional data.
method t-NEB uses density estimation, maximum density paths, and probabilistic merging.
result t-NEB yields state-of-the-art clustering performance on high-dimensional data.
ChronoMID uses neural networks to classify bone disease in mice from micro-CT scans.
problem Classifying bone disease in mice from micro-CT scans.
method ChronoMID applies cross-modal convolutional neural networks to incorporate temporal information from timestamps and difference images.
result The top-performing model achieved 99.54% accuracy, significantly outperforming a baseline CNN.
Predict and classify brain image evolution trajectories from a single MRI timepoint.
problem Diagnosing early mild cognitive impairment (eMCI) from a single MRI scan.
method Supervised and unsupervised learning frameworks that predict and label intensity patch evolution trajectories from a baseline MRI.
result Classification accuracy increased by up to 10% points compared to single timepoint-based methods.
We check the claims that data from Google Trends contain enough data to predict future financial index returns. We first discuss the many subtle (and less subtle) biases that may affect the backtest of a trading strategy, particularly when based on such data. Expectedly, the choice of keywords is crucial: by using an i…
Paper proves inequality for capillary hypersurfaces in a wedge.
problem Proving a best version of Heintze-Karcher inequality for capillary hypersurfaces.
method Utilized Heintze-Karcher method and modified parallel hypersurfaces.
result Classified capillary constant mean curvature hypersurfaces hitting the edge in a wedge.
Early detection and precise characterization of emerging topics in text streams can be highly useful in applications such as timely and targeted public health interventions and discovering evolving regional business trends. Many methods have been proposed for detecting emerging events in text streams using topic modeli…
New homology theory connects graph domination to subtle algebraic structures.
problem Understanding graph domination through algebraic homology.
method Interpreting überhomology as poset homology and showing its functorial properties.
result The Euler characteristic of bold homology equals the evaluation of the connected domination polynomial.
The lowest eigenvalue of the Schrödinger operator on a compact Riemannian manifold without boundary is studied. We focus on the particularly subtle case of a sign changing potential with positive average.
A method models continuous-time glucose distributions in children with diabetes.
problem Capturing subtle temporal changes in glucose distributions.
method Probabilistic framework using Gaussian mixtures and neural ODEs.
result Detects treatment-related improvements in glucose dynamics.
In this paper, we exploit a subtle indeterminacy in the definition of the spherical Kervaire-Milnor invariant which was discovered by R. Stong to construct non-spin 4-manifolds with even intersection form and prescribed signature.
A new metric measures time series divergence efficiently.
problem Quantifying subtle differences in time series data.
method Sequence Likelihood (SL) divergence, a generalized KL divergence for time series.
result Efficient estimators of SL divergence from finite sample paths.
New algorithm detects subtle breakpoints in IoT data.
problem Detecting subtle boundaries in IoT data sequences.
method Unsupervised deep learning approach.
result Outperforms existing changepoint detection methods.
The paper computes a pairing for knot concordance and finds non-slice knots.
problem Computing and understanding the twisted Blanchfield pairing for knot concordance.
method Combinatorial algorithm for computing the twisted Blanchfield pairing; using zero-framed surgery and Casson-Gordon representations.
result Some satellites of genus two ribbon knots are non-slice.
Simple physical modifications can fool autonomous driving systems.
problem Vulnerability of autonomous driving models to adversarial attacks.
method Demonstrated end-to-end attacks on autonomous driving using simple physical modifications.
result Simple physical modifications can induce activation patterns similar to different scenarios used in training, fooling autonomous driving models.
RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.
problem Challenges in anomaly detection and segmentation, especially in real-time applications.
method RADAR uses attention-based diffusion models to directly produce anomaly maps from the diffusion process, bypassing reconstruction.
result RADAR improves F1 score by 7% on MVTec-AD and 13% on 3D-printed material compared to state-of-the-art methods.
We argue for the principle of unchanged optimality in RL benchmarks and discuss its implications.
problem Generalization in reinforcement learning benchmarks.
method Discussion of conceptual properties and subtle choices in state representation and model architecture.
result The principle of unchanged optimality is important for RL benchmarks and can be broken or satisfied by model architecture choices.
Paper uses deep learning to detect subtle breast cancer signs.
problem Detecting subtle architectural distortion in mammograms.
method Data augmentation for training a Convolutional Neural Network (CNN).
result CNN trained on augmented data detected AD with AUC = 0.74.
MILCCI integrates labels across categories for better understanding of multi-trial data.
problem Understanding how labels encode multi-trial observations and disentangling their effects.
method Sparse per-trial decomposition leveraging label similarities within each category.
result MILCCI identifies interpretable components and integrates label information.
In Theorem 1.2 of the paper math.GT/0002110 the author claimed to have proved that all transversal knots whose topological knot type is that of an iterated torus knot (we call them cable knots) are transversally simple. That theorem is false, and the Erratum math.GT/0610565 identifies the gap. The purpose of this paper…
It is known that the number of biquandle colorings of a long virtual knot diagram, with a fixed color of the initial arc, is a knot invariant. In this paper we describe a more subtle invariant: a family of biquandle endomorphisms obtained from the set of colorings and longitudinal information.
Paper presents machine learning approach for detecting software vulnerabilities.
problem Detect subtle security vulnerabilities in production software.
method Data-driven approach using machine learning on C and C++ code.
result Highest performing model achieves AUC of 0.87 on ROC curve.
Gradient Reduction Convolutional Neural Network Policy for Financial Deep Reinforcement Learningq-fin.CP
Enhanced CNN for financial data improves predictive accuracy and stability.
problem Complexity and variability in financial data.
method Normalization and Gradient Reduction Architecture.
result Improvement in model accuracy and stability.
Theoretical analysis of vision transformers' performance with MAE and CL objectives.
problem Understanding the distinct representations learned by vision transformers with MAE and CL objectives.
method Modeling visual data distribution and analyzing ViTs training dynamics with gradient descent.
result ViTs trained with MAE objectives learn both global and local features, while CL-trained ViTs favor global features.
Lorentzian versions of classical Riemannian volume comparison theorems by Gunther, Bishop and Bishop-Gromov, are stated for suitable natural subsets of general semi-Riemannian manifolds. The problem is more subtle in the Bishop-Gromov case, which is extensively discussed. For the general semi-Riemannian case, a local v…
We examine homogeneous metrics on spheres and determine which ones have positive sectional curvature. The answer is subtle and surprisingly difficult to prove. In some cases we also determine their pinching constants. This completes the classification of all homogeneous metrics with positive curvature (apart from one s…
Study on kinetic Langevin diffusions and their couplings, showing subtle TV bounds and new non-Markovian couplings.
problem Understanding and quantifying the TV distance between solutions of kinetic Langevin diffusions with different initial values.
method Established new non-Markovian couplings for kinetic Langevin diffusions, derived from optimal coalescence trajectories, and analyzed their TV bounds.
result No Markovian coupling can capture the asymptotic decay rate of the TV distance between solutions of kinetic Langevin diffusions with different initial values.
A new test evaluates risk estimation accuracy using probability integral transform.
problem Measuring the accuracy of financial market risk estimations.
method Probability Integral Transform (PIT) of ex post realized returns against ex ante probability distributions.
result The new test shows the importance of capturing the dynamic of financial markets.
Algorithm predicts zoonotic virus emergence with high accuracy.
problem Precise spatio-temporal prediction of zoonotic virus emergence.
method Machine inference using protein sequence databases.
result Quantitative indicators of jump risk from genotypic changes.