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.

168,742 papers · 148 categories

Trend · papers per month

110219329438 · Jun 202019922001200920172026
48 results for Feature Reliability

SAEs struggle with feature consistency across runs, hindering MI reliability.

problem Inconsistency of learned SAE features across different training runs.
method Propose using the Pairwise Dictionary Mean Correlation Coefficient (PW-MCC) to measure feature consistency.
result High levels of feature consistency (0.80 for TopK SAEs on LLM activations) are achievable with appropriate architectural choices.

WCAM assesses neural network reliability by attributing decisions to wavelet scales.

problem Challenges in evaluating neural network reliability and feature robustness.
method Introduces WCAM, a wavelet-based attribution method to assess decision reliability.
result WCAM reveals where and on what scales a model focuses, enabling reliable decision assessment.

TRIP detects unreliable feature importance scores in random forests.

problem Unreliable feature importance scores in random forests due to model extrapolation.
method Develops TRIP (Test for Reliable Interpretation via Permutation) to detect unreliable permutation feature importance scores.
result TRIP reliably detects unreliable permutation feature importance scores in high-dimensional settings.

We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows reliable predictors fo…

2017-08-01abs ↗pdf ↗

DW-KNN improves KNN by integrating distance and neighbor reliability for better prediction accuracy.

problem Standard KNN assumes all neighbors are equally reliable, leading to unreliable predictions in heterogeneous feature spaces.
method DW-KNN integrates exponential distance with neighbor validity, providing instance-level interpretability and reducing hyperparameter sensitivity.
result DW-KNN achieves 0.8988 average accuracy, ranks 2nd among six methods, and has the lowest cross-validation variance.

The paper decomposes probabilistic scores into reliability, uncertainty, and information loss.

problem Understanding the reliability and uncertainty of probabilistic predictions.
method Developed decomposition identities for proper losses, quantifying reliability, residual uncertainty, and information gain.
result A three-term identity for classification scores, revealing miscalibration, grouping term, and feature-level uncertainty.

New methods for better uncertainty prediction in ML.

problem Insufficient calibration in machine learning regression.
method Conditional calibration with respect to input features (adaptivity).
result Consistency and adaptivity are complementary, and good consistency does not guarantee good adaptivity.

Enhanced visual feature attribution via adaptive baseline weighting.

problem IG's sensitivity to baseline images leads to noisy or unstable explanations.
method Weighted Integrated Gradients (WG) evaluates and weights baselines for improved reliability.
result WG improves over Expected Gradients (EG) by up to 36% across various models.

RoSHAP stabilizes feature attribution in machine learning models.

problem Stochastic variation in feature attribution measures.
method Modeling feature attribution score distribution and estimating it through bootstrap resampling and kernel density estimation.
result RoSHAP provides stable feature rankings and improves model performance.

Bayesian framework improves reliability and consistency of model explanations.

problem Inconsistent and unreliable explanations from state-of-the-art methods.
method Developed a novel Bayesian framework for generating local explanations with associated uncertainty.
result Generated explanations are consistent, stable, and provide credible intervals for feature importances.

New methods reduce extrapolation errors in feature importance.

problem Flawed feature importance methods using unrestricted permutations lead to extrapolation errors.
method Three new approaches: conditional model reliance, Knockoffs with Gaussian transformation, and restricted ALE plot designs.
result Theoretical and numerical results show our strategies reduce/eliminate extrapolation.

We consider the problem of aligning a pair of databases with jointly Gaussian features. We consider two algorithms, complete database alignment via MAP estimation among all possible database alignments, and partial alignment via a thresholding approach of log likelihood ratios. We derive conditions on mutual informatio…

2019-03-04abs ↗pdf ↗

Safe-DRFS selects features robust to covariate shifts for reliable performance.

problem Feature selection fails in diverse deployment environments.
method Safe-DRFS extends safe screening to distributionally robust settings under covariate shift.
result Safe-DRFS identifies a feature subset encompassing optimal subsets across distribution shifts.

New framework improves reliability of learned representations by modeling uncertainty and structural constraints.

problem Uncertainty in learned representations treated as deterministic, leading to unreliable models.
method Proposes a principled framework for reliable representation learning with uncertainty-aware regularization and structural constraints.
result Improves stability, calibration, and robustness of learned representations.

Two strategies for training network classifiers with feature heterogeneity.

problem Training network classifiers with agents having varying feature sizes and unreliable local decisions.
method Promotes global and local smoothing of classifier outputs.
result Output smoothing makes network classifier dynamics more complex, requiring regularization of parameters.

Survey and framework for efficient active learning in structural reliability.

problem Efficiently solving complex structural reliability problems.
method Generalized modular framework combining surrogate model, reliability estimation algorithm, learning function, and stopping criterion.
result 39 strategies for solving 20 reliability benchmark problems, highlighting the importance of surrogates and algorithms.

A new method improves feature importance and model stress-testing reliability.

problem Estimating feature contributions in machine learning models for trust and transparency.
method Replacing multiple random permutations with a single, deterministic, and optimal permutation.
result Improved bias-variance tradeoffs and accuracy in challenging scenarios.

Small sample size hinders accurate long-term COVID-19 case predictions.

problem Difficulty in predicting medium and long-term COVID-19 case trends.
method Analysis of machine learning models' performance; feature selection; comparison of different models.
result Simple linear regression models provide reliable 2-week predictions but not beyond.

Paper introduces PTL-SI for statistical inference in TL-HDR, controlling FPR.

problem Quantifying statistical significance in TL-HDR with limited data.
method PTL-SI framework for valid pp-values in TL-HDR feature selection.
result Valid pp-values and controlled FPR in TL-HDR feature selection.

Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been reported to impair the performance in certain cases. A fundamental source of err…

2018-11-27abs ↗pdf ↗

UBMF tackles fault diagnosis in imbalanced industrial data with enhanced accuracy and adaptability.

problem Fault diagnosis challenges in imbalanced industrial data.
method Integrates four key modules: data perturbation, cross-task feature extraction, uncertainty-based filtering, and Bayesian meta-knowledge integration.
result Achieves an average improvement of 42.22% across ten diagnostic tasks.

A novel feature selection method using noise-based hypothesis testing improves feature selection accuracy.

problem Challenges in feature selection for complex, high-dimensional datasets.
method Introduces multiple random noise features and evaluates feature importance against noise feature maxima using non-parametric bootstrap-based hypothesis testing.
result Outperforms existing methods in simulated and real-world datasets.

SFS-DA method statistically tests FS reliability under domain adaptation.

problem Feature selection reliability under domain adaptation with limited target data.
method Selective Inference framework to control false positive rate and enhance true positive rate.
result SFS-DA method controls FPR below a pre-specified level αα (e.g., 0.05) while maximizing true positive rate.

Combining feature importance estimates improves reliability of machine learning predictions.

problem Lack of consensus on feature importance quantification makes explanations unreliable.
method Proposes a feature importance fusion framework combining multiple quantifiers.
result Feature importance ensembles reduce prediction error by 15%.

A feature selection algorithm should ideally satisfy four conditions: reliably extract relevant features; be able to identify non-linear feature interactions; scale linearly with the number of features and dimensions; allow the incorporation of known sparsity structure. In this work we propose a novel feature selection…

2019-01-13abs ↗pdf ↗

The paper addresses interpretability issues in EBM models by improving feature selection and reducing spurious interactions.

problem Interpretability issues in EBM models, especially spurious interactions and single feature dominance.
method Alternate Cross-feature selection, ensemble features, and model configuration alteration techniques.
result Our approach improves interpretability and predictive performance of EBM models, reducing spurious interactions and single feature dominance.

Develops a statistical test for IV, improving feature selection reliability.

problem Lack of statistical justification in conventional IV-based feature selection.
method Establishes connection with Jeffreys divergence and proposes a nonparametric hypothesis test.
result The J-Divergence test provides rigorous guarantees and is more reliable than traditional IV thresholds.

Study analyzes and enhances robustness of neural networks for classification and regression.

problem Understanding and improving robustness of neural network predictions.
method Computes reachable sets of neural networks using over- and under-approximations.
result Approach outperforms adversarial attacks and state-of-the-art classifier verification methods.

The paper defines and analyzes feature complexity in DNNs, proposing metrics for feature disentanglement and evaluation.

problem Understanding and quantifying the complexity of features learned by deep neural networks.
method Proposes a definition and disentanglement of feature complexity orders, introduces metrics for reliability and over-fitting evaluation.
result Establishes a relationship between feature complexity and DNN performance, and proposes a generic mathematical tool for network compression and knowledge distillation.

This research investigates reliable local explanations for machine listening models.

problem Generating reliable local explanations for machine listening models.
method Investigates the sensitivity of SoundLIME explanations to input perturbations and proposes a novel method for identifying suitable content types.
result SoundLIME explanations are sensitive to the content in occluded input regions, and the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.

Random small feature subsets outperform FS in diverse datasets.

problem The significance of selected features in high-dimensional datasets is questionable.
method Analysis of 28 diverse datasets (microarray, RNA-Seq, etc.).
result Any arbitrary set of features performs as well as or better than selected features across datasets.

Adaptive template systems improve feature extraction from persistence diagrams for machine learning.

problem Feature extraction from persistence diagrams for machine learning.
method Adaptive template systems using CDER, GMM, and HDBSCAN algorithms.
result Adaptive template systems yield competitive and often superior results in classification tasks.

The paper develops methods to create reliable prediction sets for complex mixture models in high-dimensional data.

problem Building accurate prediction sets for high-dimensional mixture models with feature-dependent weights.
method The authors introduce a debiasing procedure and a novel interval combination strategy to construct valid prediction sets.
result The proposed method provides reliable coverage guarantees for prediction sets in high-dimensional mixture models.