The paper tackles inconsistency in removal-based explanations and proposes methods to reduce it.
problem Inconsistency in removal-based explanations.
method Established the Impossible Trinity Theorem and proposed two novel algorithms to minimize interpretation error.
result The proposed methods achieve a substantial reduction in interpretation error, up to 31.8 times lower.
CB-SLICE identifies concept-based error slices in deep learning models.
problem Systematic errors in deep learning models on specific groups.
method Concept Bottleneck Models (CBMs) and concept representations.
result CB-SLICE outperforms state-of-the-art methods in error slice identification.
MEDIDA discovers model errors in chaotic systems using sparse regression and data assimilation.
problem Model errors in chaotic systems lead to significant discrepancies between model predictions and real-world states.
method MEDIDA combines Bayesian sparse regression and data assimilation to estimate and interpret model errors from noisy observations.
result MEDIDA successfully identifies different types of model errors in the chaotic Kuramoto-Sivashinsky system.
EBLR improves time series forecasting with interpretable results.
problem Forecasting future events to reduce uncertainty.
method Iterative method starting with a base model, adding regression trees to explain errors at each iteration.
result EBLR substantially improves base model performance through extracted features and provides comparable performance to other methods.
Adaptive spectral RL method enhances RL performance and interpretability.
problem Balancing interpretability and performance in reinforcement learning.
method Spectral based linear RL approach with adaptive regularization.
result Near-optimal bounds for parameter estimation and generalization error.
New truthful calibration errors improve model ranking in multiclass prediction.
problem Non-truthful calibration errors can mislead model comparisons.
method Introduced perfectly truthful calibration errors for multiclass predictions.
result Truthful calibration errors preserve decision-theoretic dominance and stabilize model rankings.
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 learns graph structure for multi-task learning, revealing interpretable relationships.
problem Learning relationships among tasks in multi-task learning.
method Simultaneously learns graph structure and model parameters, optimizing the graph structure with the model parameters.
result Reduces generalization error and reveals interpretable sparse graph among tasks.
In safety-critical applications a probabilistic model is usually required to be calibrated, i.e., to capture the uncertainty of its predictions accurately. In multi-class classification, calibration of the most confident predictions only is often not sufficient. We propose and study calibration measures for multi-class…
Deep learning has become increasingly popular in both supervised and unsupervised machine learning thanks to its outstanding empirical performance. However, because of their intrinsic complexity, most deep learning methods are largely treated as black box tools with little interpretability. Even though recent attempts …
Study validates saliency maps of GNNs using selective inference.
problem Reliability of GNN saliency maps in graph-structured data.
method Statistical testing framework with selective inference to control Type I error rate.
result Valid p-values for salient subgraphs, ensuring meaningful information. Local surrogate model improves time series forecasts and provides interpretable explanations.
problem Improving time series forecasting accuracy while maintaining interpretability.
method A local surrogate model is used to correct the base model's predictions, making the corrections interpretable by re-fitting the base model to the error-predicted data.
result The method can discover and explain underlying patterns in the data, improving both accuracy and interpretability.
This paper refines human labeling as a measurement process, revealing four sources of variation.
problem Systematic variation in human labeling obscures model learning.
method Introduces a statistical framework to decompose labeling outcomes.
result Empirical evidence for four components of labeling variation.
The paper proposes a method to improve forecast combination accuracy using portfolio theory.
problem Improving forecast accuracy by combining multiple forecasts.
method Generates forecast combinations using a portfolio analogy, allowing negative weights for hedging.
result Demonstrates improved performance in weighted random forest forecasts.
Dynamic CBDT improves treatment effect estimation in clinical data.
problem Estimating heterogeneous treatment effects in observational data with high accuracy and interpretability.
method Dynamic Regularized Causal Boosted Decision Trees (CBDT) integrating variance regularization and calibration.
result Significantly improved estimation accuracy and reliable coverage of true treatment effects.
PCBM improves neural network generalization by partially observing concepts.
problem Decreased generalization performance due to observing all concepts in CBM.
method Developed a theoretical analysis of PCBM's Bayesian generalization error.
result PCBM's generalization error is lower than CBM's due to partial concept observation.
Optimizes biomanufacturing processes with a new digital twin calibration method.
problem Lack of interpretability and sample efficiency in traditional DoE methods.
method Developed a computational approach to calibrate Bio-SoS digital twin model.
result Guides sample-efficient and interpretable DoEs by quantifying sub-model parameter estimation errors.
The paper extends influence functions to sequence tagging tasks for better model interpretability.
problem Lack of interpretability methods for sequence tagging models.
method Define and compute influence of training instance segments on test segment predictions.
result The segment influence method tracks with true influence and identifies annotation errors.
Machine-generated interpretations do not improve users' guessing accuracy in image classifiers.
problem Determining the usefulness of machine-generated explanations for deep neural networks.
method Human evaluation of crowd workers guessing incorrectly predicted labels with and without visual interpretations.
result Showing machine-generated visual interpretations decreased average guessing accuracy by about 10%.
The paper connects ABC to GBI, suggesting ABC as a robustification strategy.
problem Approximate Bayesian Computation struggles with tractability in complex simulators.
method Reinterpreting ABC as an implicitly defined error model and suggesting GBI.
result ABC can be seen as a robustification strategy for approximating Bayesian posteriors.
Unified model detects transferable variables and source data in high-dimensional linear regression.
problem Scarcity of target data and heterogeneity of source and target data distributions.
method UTrans model, estimation error bounds, hypothesis testing for source detection.
result UTrans achieves lower estimation and prediction errors than existing methods.
New approach interprets Nyström for kernel machines with geometric insight.
problem No comparative study over Nyström-based kernel machine approaches.
method Developed a new approach with geometric interpretation, showing equivalence to existing methods.
result Proposed approach offers insights into approximation errors and accuracy.
The paper offers error bounds for quantized dynamical models.
problem Accuracy of dynamical models from dependent data sequences.
method Developed uniform error bounds for quantized models and imperfect optimization algorithms.
result Unified bounds for slow and fast rates, scaling with model encoding bits.
The macroeconomic climate influences operations with regard to, e.g., raw material prices, financing, supply chain utilization and demand quotas. In order to adapt to the economic environment, decision-makers across the public and private sectors require accurate forecasts of the economic outlook. Existing predictive f…
Hallucinations in models are mislinked estimates, not errors.
problem Hallucinations in generative models as failures to link estimates to plausible causes.
method Formalized hallucinations, showed even optimal estimators hallucinate, provided a general lower bound on hallucinate rate, reframed hallucination as structural misalignment, and experimentally supported theory.
result Hallucinations are structural misalignments between loss minimization and human-acceptable outputs, leading to estimation errors.
Calibration without labels in multiple testing
problem Interpretable error probabilities in large-scale hypothesis testing
method Constructing pseudo-labels from spacings of ordered p-values result Finding that q-value can be severely miscalibrated This manuscript proposes a probabilistic framework for algorithms that iteratively solve unconstrained linear problems Bx=b with positive definite B for x. The goal is to replace the point estimates returned by existing methods with a Gaussian posterior belief over the elements of the inverse of B, which can …
TCE measures calibration error with a test-based approach.
problem Measuring calibration error of probabilistic binary classifiers.
method TCE uses a novel loss function based on a statistical test.
result TCE offers clear interpretation, consistent scale, and enhanced visual representation.
Meta-learning approach to learn interpretable models from human feedback.
problem Tackling the challenge of making machine learning models interpretable.
method A meta-learning approach where a model of non-trivial proxies of human interpretability is learned from human feedback, then incorporated into the ML training process to optimize for interpretability.
result The approach leads to formulas that are either significantly more or equally accurate while being more interpretable.
This work presents a technique for statistically modeling errors introduced by reduced-order models. The method employs Gaussian-process regression to construct a mapping from a small number of computationally inexpensive `error indicators' to a distribution over the true error. The variance of this distribution can be…
In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would therefore benefit from control over the finite-sample error rate of interpretations…
causalKANs provides interpretable treatment effect estimates using neural networks.
problem The opacity of deep neural networks limits their adoption in sensitive domains.
method Proposes causalKANs, a framework that transforms neural estimators into interpretable closed-form formulas.
result causalKANs performs on par with neural baselines in CATE error metrics and offers a favorable accuracy--interpretability trade-off.
Ex ante forecast outcomes should be interpreted as counterfactuals (potential histories), with errors as the spread between outcomes. Reapplying measurements of uncertainty about the estimation errors of the estimation errors of an estimation leads to branching counterfactuals. Such recursions of epistemic uncertainty …
We propose a method to extract interpretable rules from tree ensembles.
problem Tree ensembles are accurate but hard to interpret.
method Propose an estimator to extract compact sets of decision rules from tree ensembles.
result Our estimator improves accuracy and reveals useful relationships in the data.
ParaRNN improves RNN interpretability and parallelizability for time-dependent data.
problem Limited interpretability and slow training of RNNs.
method Parallelized RNN with additive representation and recurrence features.
result ParaRNN achieves comparable performance to vanilla RNNs but with improved interpretability and efficiency.
New decision-theoretic calibration error metric improves prediction reliability.
problem Improving the reliability of predictions for decision-making.
method Proposed Calibration Decision Loss (CDL) and an efficient algorithm to achieve near-optimal CDL.
result Near-optimal CDL guarantees vanishing payoff loss from miscalibration.
This paper concerns error bounds for recursive equations subject to Markovian disturbances. Motivating examples abound within the fields of Markov chain Monte Carlo (MCMC) and Reinforcement Learning (RL), and many of these algorithms can be interpreted as special cases of stochastic approximation (SA). It is argued tha…
Directly estimates CQC, improving interpretability and accuracy.
problem Inability to model and interpret CQC due to inversion issue.
method Direct doubly robust estimation of CQC without inversion.
result Improved estimation accuracy and interpretability.
Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-critical context. Concretely, we propose to use them to add introspection and error detection capabilities to neural network classifiers. Fir…
Analyzes error sources in global feature effect estimation methods.
problem Unexplored error sources in global feature effect estimation methods.
method Systematic, estimator-level analysis of bias and variance.
result Holdout data is theoretically cleanest, but estimation variance depends on sample size and model characteristics.
DCIts interprets complex time series data with interpretable coefficients.
problem Interpreting nonlinear multivariate time series data.
method Deep convolutional architecture with a Focuser and Modeler components.
result DCIts provides interpretable coefficients and interaction patterns.
In the past few years, there are several researches on Parkinson's disease (PD) recognition using single-photon emission computed tomography (SPECT) images with deep learning (DL) approach. However, the DL model's complexity usually results in difficult model interpretation when used in clinical. Even though there are …
Optimizes calibration error estimators for better classifier trustworthiness.
problem Lack of guidance on selecting and tuning calibration error estimators.
method Reformulates calibration estimation as a regression problem with i.i.d. input pairs.
result Demonstrates the effectiveness of optimized calibration estimators on image classification tasks.
This lecture presents recent advances in the theory of errors propagation. We first explain in which cases the propagation of errors may be performed with a first order differential calculus or needs a second order differential calculus. Then we point out the link between error propagation and the concept of second ord…
A new model for dynamic covariance recovery in neuroimaging data.
problem Estimating time-varying covariances in high-dimensional neuroimaging data.
method Nonconvex factorization into sparse spatial and smooth temporal components, combined with spectral initialization and gradient descent.
result The proposed method achieves linear convergence and superior performance compared to existing approaches.
Study examines human factors in radiographic testing to improve inspection performance.
problem Insufficient consideration of human and organizational factors in NDT.
method CREAM method applied to analyze and model HOF on radiogram interpretation tasks.
result Model CREAM well-adapted for estimating HOF impact on NDT performances.
After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an interpretable and factorized representation of latent variable by modifying their objec…
The concept of refinement from probability elicitation is considered for proper scoring rules. Taking directions from the axioms of probability, refinement is further clarified using a Hilbert space interpretation and reformulated into the underlying data distribution setting where connections to maximal marginal diver…