Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational formulation of black-box interpretation, general interpretability research rely hea…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Interpretable Diagnostics”
Applying machine learning in the health care domain has shown promising results in recent years. Interpretable outputs from learning algorithms are desirable for decision making by health care personnel. In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction. We focus…
Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplificationcs.LG
This paper simplifies deep ReLU networks into local linear models for better interpretability.
problem Limited transparency and interpretability of deep neural networks, especially ReLU networks.
method Local linear representation and equivalent set of local linear models (LLMs).
result Simplified deep ReLU networks for better interpretability and diagnostics.
Reducing ICD-10 code granularity improves cost model accuracy and stability.
problem High-dimensional regression with ICD-10 codes leads to unstable coefficient estimates.
method Log-linear analytics approach to cost model regularization through diagnostic code merging.
result Reducing ICD-10 code granularity from 7 characters to 6 or fewer improves model interpretability and consistency.
Proposes PRMs for interpreting financial risk concept drift.
problem Concept drift in high-stakes predictions like credit risk.
method Probabilistic Rule Models (PRMs) using Markov Logic Networks.
result Interpretable rules explain borrower risk changes.
An Easy to Interpret Diagnostic for Approximate Inference: Symmetric Divergence Over Simulationscs.LG
Paper introduces a diagnostic for approximate inference methods.
problem Estimating errors in probabilistic inference algorithms, especially for approximate methods.
method Repeatedly simulate datasets from the prior and perform inference on each, estimating a symmetric KL-divergence.
result A diagnostic for approximate inference methods can be estimated using symmetric KL-divergence.
GeoTop resolves topological ambiguity in diagnostic imaging using geometric-topological analysis.
problem Topological equivalence between benign and malignant structures in diagnostic images.
method Combines Topological Data Analysis and Lipschitz-Killing Curvatures to resolve ambiguity.
result Achieves 3.6% accuracy improvement and reduces false positives/negatives by 15-18%.
Trustworthy Predictive Distributions for Tail Events with Semiparametric Diagnostic Transport Mapsstat.ML
Paper improves predictive distributions for rare events using a simple framework.
problem Local miscalibration of predictive distributions for rare events.
method Semiparametric diagnostic transport maps to correct tail probabilities.
result Semiparametric maps improve predictions for severe weather hazards.
L-C2ST improves local diagnostics for SBI approximations.
problem Evaluating trustworthiness of posterior approximations in SBI.
method Local evaluation of posterior estimators at any observation.
result Offers better statistical power and interpretability.
Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics. However, standard formulations of supervised Latent Dirichlet Allocation have two problems. First, when documents have many more words than labels, the influence of the labels w…
Machine learning augmented diagnostic testing to identify sources of variability in test performancecs.LG
Machine learning improves diagnostic test accuracy for bovine tuberculosis.
problem Improving diagnostic test sensitivity for bovine tuberculosis.
method Machine learning to assess risk landscapes and predict infection.
result Test sensitivity improved, detecting 240 more infected herds per year.
New approach interprets machine learning models through feature space transformations.
problem Interpreting models with strongly dependent features in high-dimensional spaces.
method Feature space transformations, including PCA and partial orthogonalization.
result Enhances model interpretation tools for domain experts.
A method for interpreting SVMs using polynomial kernels, revealing model complexity.
problem Interpreting SVMs built with truncated orthogonal polynomial kernels.
method Orthogonal Representation Contribution Analysis (ORCA) with normalized Orthogonal Kernel Contribution (OKC) indices.
result The method reveals structural aspects of model complexity not captured by predictive accuracy.
GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.
problem Efficiently solving Stochastic Optimal Transport with hard terminal distributions and soft costs.
method Guided Harmonic Path-Integral Diffusion (GH-PID) framework with low-dimensional guidance.
result GH-PID generates geometry-aware, cost-reducing trajectories that match terminal distributions.
LADaR framework calibrates machine learning models for instance-wise predictions.
problem Challenges in assessing and calibrating predictive distributions for complex inputs.
method Local Amortized Diagnostics and Reshaping of Conditional Densities (LADaR) framework and algorithm.
result Achieves better instance-wise calibration than existing methods in galaxy distance estimation.
Paper proposes a diagnostic tool for evaluating model performance out-of-sample.
problem Evaluating model performance on unseen data.
method Uses a finite calibration dataset to assess future losses.
result Provides guarantees under weak assumptions and quantifies distribution shifts.
A new HP model balances interpretability and flexibility for EHR event sequences.
problem Balancing interpretability and flexibility in modeling diagnostic event sequences.
method Proposes a neural network-based HP with flexible impact kernel and transformer layers.
result Accurately recovers impact functions, competitive performance, and clinically meaningful interpretation.
Improved 3D ECG feature attributions for clinical interpretation.
problem Lack of interpretability in deep learning models for 12-lead ECG analysis.
method Cross-modal mapping of feature attributions from 12-lead ECG models onto CineECG 3D space.
result Mapped feature attributions yield higher Dice scores than standard 12-lead attributions.
Language models fail to process hallucinated responses, and this study diagnoses the failure.
problem Language models fail to process hallucinated responses, leading to over-concentration or diffuse attention.
method The study uses forced scoring of benchmark-labeled responses to compute attention shapes and analyze the symmetric component of the degree-normalized attention operator.
result The study proves that every transpose-invariant spectral diagnostic of the attention operator is orientation-blind and bounds the sensitivity of any Lipschitz diagnostic by the asymmetry coefficient \(G\).
Unified framework explains few-shot multimodal medical imaging performance.
problem Limited labeled data in rare diseases and low-resource settings.
method PAC learning, VC theory, PAC Bayesian analysis, information gain, Chain of Thought reasoning.
result Unified theoretical framework for few-shot multimodal medical imaging.
This work proposes validation diagnostics for SBI algorithms using Normalizing Flows.
problem Lack of appropriate validation methods for SBI algorithms with complex, high-dimensional data.
method Develops validation diagnostics based on Normalizing Flows with theoretical guarantees.
result Offers theoretical guarantees on consistency of NF-based estimators.
We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the the search for counterfactual instances and …
We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importance scores to each word of an instance by exploiting syntactic constituency structure. We establish an axiomatic characterization of these i…
Proposes a model to interpret complex ML algorithms.
problem Complex ML models are hard to interpret.
method Uses model-based regression trees and interpretable main-effects models.
result Surrogate model provides interpretable results with good predictive performance.
Distillation and Interpretability of Ensemble Forecasts of ENSO Phase using Entropic Learningphysics.comp-ph
Paper distills ensemble ENSO forecasts into simpler models for better diagnostics.
problem Interpreting complex ensemble ENSO forecasts.
method Aggregates eSPA ensemble members that correctly predict ENSO phase.
result Compact distilled models maintain forecast performance and enable diagnostics.
Cockpit provides tools for debugging deep neural networks during training.
problem Limited real-time training diagnostics for deep learning models.
method Cockpit uses novel higher-order information about gradient distribution and curvature.
result Facilitates identification of learning phases and failure modes.
ReGEN-TAD detects anomalies in financial time series with interpretable models.
problem Detecting anomalies in complex financial time series with high-dimensional data.
method Integrates machine learning with econometric diagnostics in a refined convolutional--transformer architecture.
result Unified anomaly score without labeled data, robust to structured deviations.
CB-APM uses analyst consensus as a bottleneck to interpret stock returns.
problem Tackles the challenge of understanding and predicting stock returns using professional beliefs.
method Embeds analyst consensus as a structural bottleneck, treating it as a sufficient statistic for market information.
result CB-APM portfolios exhibit strong monotonic return gradients and robust across different economic conditions.
Bayesian model averaging under predictor redundancy
problem Reporting Bayesian model averaging posterior without changing the Bayesian target
method Using hard or soft regions of support space
result Region reports often give shorter and clearer summaries while preserving the main posterior information
TRACE analyzes risk changes in models trained on shifted data.
problem Understanding performance changes when a model trained on shifted data is used.
method TRACE framework decomposes risk change into four factors: generalization gaps, model change penalty, and covariate shift penalty.
result TRACE provides a diagnostic tool to understand and quantify risk changes due to covariate shift.
New framework uses geometry of embeddings to predict robustness.
problem Monitoring robustness in models without OOD labels.
method Constructs graphs from embeddings, measures spectral complexity and curvature.
result Representation geometry predicts robustness reliably.
Systematic review of multimodal data challenges and solutions.
problem Challenges in integrating diverse data types for improved diagnostics and personalized care.
method Synthesizing findings from 69 studies on technical obstacles and recent methodological advances.
result Promising solutions like transfer learning, generative models, attention mechanisms, and neural architecture search.
The PARAFAC tensor decomposition has enjoyed an increasing success in exploratory multi-aspect data mining scenarios. A major challenge remains the estimation of the number of latent factors (i.e., the rank) of the decomposition, which yields high-quality, interpretable results. Previously, we have proposed an automate…
Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancystat.ML
A new method calculates intrinsic effective sample size for manifold-valued data.
problem Challenges in choosing effective sample size for manifold-valued data.
method Proposes an intrinsic effective sample size based on kernel discrepancy.
result Establishes an exact finite-sample risk interpretation and consistency of the estimator.
We identify spectral conditions for reliable neural probe interpretation.
problem Unreliable performance of linear probes in interpreting neural representations.
method Formalized Spectral Identifiability Principle (SIP) based on eigengap and Fisher error.
result Reliability of neural probes depends on the eigengap relative to Fisher estimation error.
Method extracts time-localized clusters to explain deep learning models in ECG analysis.
problem Limited understanding of deep learning models in ECG analysis.
method Extracts time-localized clusters from model's internal representations.
result Enhances trust in AI-driven diagnostics and reveals clinically relevant patterns.
IGSD separates task-specific content channels in transformer components by comparing activation replacement with zero ablation.
problem Mechanistic interpretability of transformer components
method IGSD: paired-intervention framework for comparing activation replacement with zero ablation
result IGSD identifies an early-layer content channel in transformer components that standard importance methods underestimate.
Establishes statistical and computational bounds for influence diagnostics.
problem Identifying influential datapoints or subsets in machine learning models.
method Finite-sample statistical bounds and computational complexity for influence functions and approximate maximum influence perturbations.
result Established statistical and computational guarantees for influence diagnostics.
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
The article explains how to estimate confusion matrices for classifiers using unlabeled data.
problem Estimating sensitivity and specificity of binary medical diagnostic tests without gold standard tests.
method Modifying diagnostic test solutions to estimate confusion matrices for classifiers on unlabeled data.
result The approach can be used to estimate accuracy statistics for supervised or unsupervised binary classifiers on unlabeled data.
Supervised Machine Learning (SML) algorithms such as Gradient Boosting, Random Forest, and Neural Networks have become popular in recent years due to their increased predictive performance over traditional statistical methods. This is especially true with large data sets (millions or more observations and hundreds to t…
VDA improves disentanglement of latent representations in complex signals.
problem Learning disentangled and interpretable representations in nonstationary, high-dimensional time-evolving signals.
method Variational decomposition autoencoding (VDA) framework, incorporating signal decomposition, contrastive self-supervised task, and variational prior approximation.
result DecVAEs surpass state-of-the-art VAE-based methods in disentanglement quality and generalization.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
Proposes a framework to explain KS deterioration in credit risk models.
problem Inconsistent and ad hoc diagnosis of KS decline in credit risk models.
method Counterfactual diagnostic framework attributing KS decline to sampling variability, portfolio composition, covariate shift, and residual deterioration.
result The proposed approach provides more interpretable and governance-relevant explanations than threshold-based review alone.
AI enhances cancer diagnostics using spectroscopy.
problem Early and accurate cancer diagnosis.
method Combining AI with spectroscopy-based techniques.
result AI improves cancer diagnostics speed and safety.
Assessing and improving reliability of neighbor embedding methods: a map-continuity perspectivestat.ME
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
bioLeak addresses data leakage in biomedical machine learning studies.
problem Data leakage causes optimistic bias in machine learning models for biomedical studies.
method bioLeak provides leakage-aware resampling workflows and model audits in R.
result The package supports various machine learning tasks and can detect leakage mechanisms.
A new framework bridges classical and machine learning methods for reliable inference from complex models.
problem Intractable likelihood functions in complex systems make classical statistics ineffective for likelihood-free inference.
method Likelihood-Free Frequentist Inference (LF2I) framework that combines classical statistics and machine learning.
result Valid confidence sets with near finite-sample validity can be constructed for any parameter value.