Research
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.

169,341 papers · 148 categories

Trend · papers per month

2935868781,171 · Jun 202019922001200920182026
48 results for data perturbations

The paper explores maximal perturbations to hide certain attributes in data while keeping the model's performance intact.

problem Protecting sensitive attributes from both model and human detection.
method Adversarial perturbations applied to raw data to conditionally damage model's classification of one attribute while preserving the rest.
result Maximal perturbations can hide certain attributes from both model and human detection, impacting model performance but not human perception.

The paper tackles extrapolation of gene knockouts effects on RNA counts.

problem Modeling effects of gene knockouts on RNA counts for new perturbations.
method Formulated as a latent variable model with additive perturbation effects, proved identifiability, proposed PDAE for estimation.
result PDAE can accurately predict effects of unseen but identifiable perturbations.

A new framework for differentially private ERM using input perturbation.

problem Ensuring privacy in empirical risk minimization with randomized data.
method Input perturbation where each data contributor independently randomizes their data.
result The model learned with input perturbation satisfies differential privacy and local differential privacy.

Proposes a new method to identify important input features using maximally invariant data perturbation.

problem Lack of formal mathematical definitions for feature scoring in complex machine learning models.
method Formulates the problem as linear programming to find the maximally invariant data perturbation.
result Identifies relevant parts of images effectively, distinguishing important input features.

Generative Intervention Models predict perturbation effects without knowing the underlying mechanisms.

problem Predicting perturbation effects when the mechanisms are unknown.
method Generative Intervention Models (GIM) that map perturbation features to distributions over atomic interventions in a causal model.
result GIMs achieve robust out-of-distribution predictions and infer underlying perturbation mechanisms.

The paper learns perturbation sets from data to improve robustness in machine learning.

problem Real-world perturbations are not well characterized in adversarial defenses.
method A conditional generator defines perturbation sets over latent space, with properties for quality measured.
result Learned perturbation sets generate diverse, meaningful perturbations and improve model robustness.

This paper tackles incomplete multi-view clustering with spectral perturbation theory.

problem Realistic clustering scenario where data instances are missing in certain views.
method Spectral perturbation theory and matrix completion method for incomplete similarity matrix.
result The minimization of perturbation risk bounds maximizes the final fusion result across all views.

Improved generalization with semantic perturbations using normalizing flows.

problem Overfitting in deep neural networks training.
method Use normalizing flows for generating semantically meaningful perturbations in latent space.
result Achieved 96.6% test accuracy on CIFAR-10 with ResNet-18, outperforming existing methods.

New method for analyzing compositional data, addressing biases in summary statistics.

problem Inadequate effect measures for compositional data, especially in high-dimensionality and sparsity.
method Perturbation-based effect measures, average perturbation effects.
result Proposed estimators efficiently estimate average perturbation effects, outperforming existing techniques.

CROSSGRAD learns general classifiers from multi-domain data without adaptation.

problem Learning classifiers that generalize across different domains.
method Cross-gradient training using domain-guided perturbations and Bayesian sampling.
result CROSSGRAD achieves better generalization to unseen domains compared to existing methods.

DDL technique improves accuracy of deep neural networks against adversarial perturbations.

problem Improving accuracy of deep neural networks in the presence of adversarial perturbations.
method Denoising Dictionary Learning (DDL) technique applied to MNIST and CIFAR10 datasets.
result DDL significantly improves reconstruction quality and accuracy of deep neural networks on perturbed data.

DIP-FAT improves adversarial training by diversifying perturbations.

problem Adversarial examples fool deep neural networks, leading to overfitting and poor performance.
method DIP-FAT uses random directions to diversify perturbations in adversarial training.
result DIP-FAT reduces overfitting and improves clean data accuracy.

Constructs perturbations of a minimal surface with triple junctions.

problem Minimal surfaces with triple junctions in curved spaces.
method Constructs stationary perturbations with given boundary conditions.
result Constructs minimal surfaces with triple junctions in R2imesS1\mathbb{R}^2 imes \mathbb{S}^1.

The paper assesses machine learning robustness with covariate perturbations.

problem Ensuring robustness of machine learning models against adversarial attacks and data changes.
method Proposes a framework using covariate perturbation techniques to assess model robustness.
result Demonstrates the effectiveness of the approach in comparing robustness across models and identifying instabilities.

Wide networks learn from adversarial perturbations effectively.

problem Understanding why adversarial examples deceive classifiers and transfer between models.
method Assumed wide two-layer networks, proved with theoretical analysis.
result Adversarial perturbations contain class-specific features for networks to generalize.

EVILL uses randomised perturbations to improve exploration in bandit problems.

problem Improving exploration in structured stochastic bandit problems.
method Solves for the minimiser of a linearly perturbed regularised negative log-likelihood function.
result EVILL matches the performance of Thompson-sampling-style methods in theory and practice.

A new approach to maximum likelihood learning of discrete graphical models and RBM in particular is introduced. Our method, Perturb and Descend (PD) is inspired by two ideas (I) perturb and MAP method for sampling (II) learning by Contrastive Divergence minimization. In contrast to perturb and MAP, PD leverages trainin…

2014-05-06abs ↗pdf ↗

Novel framework uses synthetic data to quantify uncertainty in complex data.

problem Uncertainty quantification in complex, unstructured data.
method Perturbation-Assisted Sample Synthesis (PASS) and Perturbation-Assisted Inference (PAI) framework.
result Statistically guaranteed validity in inference, enhancing reliability of synthetic data.

Paper introduces input perturbation for privacy in machine learning models.

problem Protecting both training data and model parameters while maintaining privacy.
method Add noise to training data and train with perturbed data for differential privacy.
result Achieves (ε,δ)-differential privacy on the final model with privacy on original data.

The paper examines the reliability of limit order book representations in the face of data perturbation.

problem The reliability of limit order book representations under data perturbation.
method Experimental analysis of existing representations and guidelines for future research.
result Existing representations of limit order book data are vulnerable to data perturbation.

A detector subnetwork improves deep learning robustness against adversarial perturbations.

problem Vulnerability of deep neural networks to adversarial perturbations that are imperceptible to humans.
method Augmenting deep neural networks with a binary classification detector subnetwork trained to distinguish adversarial from genuine data.
result Adversarial perturbations can be detected surprisingly well even though they are imperceptible to humans.

CausalRegNet generates accurate data for gene perturbation experiments, improving CSL methods.

problem Assessing and selecting causal structure learning methods in gene perturbation experiments.
method CausalRegNet, a multiplicative effect structural causal model, generates accurate observational and interventional data.
result CausalRegNet generates more accurate distributions and scales better than current simulation frameworks.

Evolutionary algorithm finds optimal pixel perturbations to improve neural network generalization.

problem Minimal data corruption by pixel modifications causes overfitting in neural networks.
method Evolutionary algorithm with a novel cost function to maximize generalization gap and domain divergence.
result Method outperforms previous pixel-based data distribution shift methods on CNNs.

Ensemble methods improve neural networks' accuracy and robustness against adversarial perturbations.

problem Adversarial perturbations can cause deep learning models to misclassify.
method Used ensemble methods to defend against adversarial perturbations.
result Ensemble methods improve accuracy and robustness of neural networks against adversarial attacks.

SmoothFool efficiently computes smooth adversarial perturbations for deep networks.

problem Vulnerability of deep neural networks to adversarial attacks with specific statistical properties.
method SmoothFool: a general and computationally efficient framework for computing smooth adversarial perturbations.
result Smoothness significantly enhances robustness against adversarial attacks and improves transferability.

New approach to adversarial robustness with non-uniform perturbations.

problem Real-world adversaries craft adversarial examples with non-uniform perturbations.
method Proposes non-uniform perturbations based on feature dependencies and data distribution.
result Shows improved robustness to real-world attacks compared to uniform perturbations.

Study on stability of GCNNs under graph perturbations.

problem Limited theoretical understanding of GCNN stability.
method Proposes a probabilistic framework to analyze GCNN stability under various graph perturbations.
result Demonstrates the importance of data distribution in stability analysis.

This study benchmarks transcriptomics models for perturbation analysis, finding scVI and PCA superior.

problem Limited evaluation of transcriptomics foundation models for perturbation analysis.
method Developed a novel evaluation framework using diverse public datasets from different sequencing techniques and cell lines.
result scVI and PCA identified as superior models for understanding biological perturbations.

New method stabilizes private LASSO for high-dimensional data with diverse covariate scales.

problem Privacy constraints and heterogeneity in covariate scales degrade LASSO stability and accuracy.
method Gram-based anisotropic objective perturbation to counteract covariate structure.
result Significantly improves convergence and statistical efficiency of private LASSO estimators.

Lower class selectivity makes networks more robust to natural perturbations but more vulnerable to adversarial attacks.

problem Understanding how class selectivity affects robustness to different types of perturbations in neural networks.
method Investigated the relationship between class selectivity and robustness to natural and adversarial perturbations in neural networks.
result Lower class selectivity increases robustness to natural perturbations but decreases robustness to adversarial attacks.

Study on low-dimensional adversarial perturbations in classification models.

problem Understanding and quantifying the effectiveness of low-dimensional adversarial perturbations.
method Analytical lower-bounds for fooling rate, considering binary classifiers under generic regularity conditions.
result Rigorous explanation for the success of heuristic methods in generating low-dimensional adversarial perturbations.

Proposes elliptical transformation for improving machine learning performance in perturbation models.

problem Performance degradation of machine learning techniques in transform domain due to feature pattern differences.
method Introduces a nonlinear parametric perturbation model that transforms input feature patterns to elliptical patterns, and applies flexible block-wise dimensionality reduction.
result The proposed method outperforms PCA in classification performance and data privacy protection.

The paper compares methods for imputing missing categorical data in supervised classification tasks.

problem Missing data in categorical variables can degrade model performance.
method Experimented on two datasets with missing categorical data, comparing imputation methods with and without additional missing-data perturbation.
result Imputation methods can increase predictive accuracy in the presence of missing-data perturbation.

Graph neural networks detect structural perturbations from time series data.

problem Detecting structural causes of disturbances in complex systems.
method Graph neural network approach to infer structural perturbations from functional time series.
result Data-driven approach outperforms typical reconstruction methods and meets Bayesian inference accuracy.

Graph scattering transforms are stable to metric perturbations of network topology.

problem Stability of graph data representations under metric perturbations.
method Extending scattering transforms to network data using multiresolution graph wavelets and graph convolutions.
result Graph scattering transforms are stable to metric perturbations of the underlying network topology.