This dissertation tackles challenges in reliable machine learning measurement.
problem Challenges in reproducibility, scalability, and uncertainty quantification in machine learning.
method Develops criteria for meaningful metrics and methodologies for scalable, reliable measurement.
result Provides methods for evaluating generative-AI systems and quantifying memorization.
Study evaluates machine learning methods for large-scale network reliability, revealing ANN's and PR's performance.
problem Tackles the NP-hard problem of approximating binary-state network reliability for large-scale systems.
method Compares 20 machine learning methods across three reliability regimes and evaluates their performance on large-scale networks.
result Large-scale networks with arc reliability ≥ 0.9 exhibit near-unity system reliability, enabling computational simplifications.
m-arcsinh improves SVM and MLP reliability and speed in scikit-learn.
problem Improving SVM and MLP reliability and speed in scikit-learn.
method Modified arcsinh function for kernel and activation in SVM and MLP.
result Competitive classification performance and reliability of SVM and MLP with m-arcsinh.
Study finds machine learning interpretations are often unstable and unreliable.
problem Reliability of machine learning interpretations in high-stakes domains.
method Stability study on global interpretations using tabular data.
result Popular interpretation methods are frequently unstable, less stable than predictions, and not associated with prediction accuracy.
Synthesizes machine learning applications in reliability and safety.
problem Navigating the fragmented literature on ML for reliability and safety.
method Overview of ML categories, review of applications, discussion of Deep Learning.
result Machine learning can provide novel insights and improve accident prevention.
MAntRA combines machine learning and Bayesian methods for time-dependent reliability analysis of unknown systems.
problem Time-dependent reliability analysis of systems with unknown governing physics.
method Combines machine learning, Bayesian statistics, and stochastic integration to discover and analyze SDEs from data.
result Demonstrates the effectiveness of MAntRA on three numerical examples, indicating its potential for in-situ and heritage structure analysis.
The article proposes optimal learning strategies for machine learning-based reliability analysis.
problem Improving computational efficiency and accuracy in machine learning-based reliability analysis.
method Theorems and mathematical proofs for optimal learning strategies considering and neglecting correlations among design samples.
result The optimal learning strategy considering Kriging correlation outperforms other methods in terms of reduced evaluations of performance functions.
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.
Adaptive Quantum Conformal Prediction improves reliability of quantum machine learning predictions.
problem Quantum machine learning lacks robust uncertainty quantification methods.
method Adaptive Conformal Inference applied to quantum conformal prediction to maintain validity over time.
result AQCP achieves target coverage levels and is more stable than standard quantum conformal prediction.
DeepONet accelerates reliability analysis of stochastic nonlinear systems.
problem Time-dependent reliability analysis of systems with stochastic forcing.
method DeepONet, a novel operator network, learns function-to-function mappings.
result DeepONet efficiently and accurately predicts system responses.
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.
Improves reliability diagrams for probabilistic forecasts.
problem Lack of stability in reliability diagrams hampered their use.
method CORP approach using non-parametric isotonic regression and PAV algorithm.
result Improved reliability diagrams with statistical consistency and reproducibility.
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.
Proposes incorporating noise sources in machine learning evaluation for more reliable conclusions.
problem Inadequate handling of nondeterminism in machine learning research leads to unreliable results.
method Uses linear mixed effects models (LMEMs) and generalized likelihood ratio tests (GLRT) to analyze performance evaluation scores and assess performance differences.
result Demonstrates how to incorporate various sources of noise and data properties into statistical significance testing and reliability analysis.
New framework assesses extreme errors in machine learning models.
problem Current validation methods fail to quantify extreme errors in high-stakes domains.
method Uses Extreme Value Theory (EVT) to estimate worst-case failures.
result Establishes EVT as a fundamental tool for assessing model reliability.
Paper proposes NeuroAttack to undermine SNNs security through bit-flips.
problem Security and reliability issues in SNNs.
method Cross-layer attack exploiting low-level reliability issues via adversarial input noise.
result Serious integrity threat to SNNs and DNNs.
A framework integrates machine learning with robust control for safer, more reliable systems.
problem Combining machine learning with robust control for systems with stringent safety and reliability requirements.
method Integrates Gaussian Process Regression and state-of-the-art robust controller synthesis within a framework that provides rigorous guarantees.
result Demonstrated improved performance with more data while maintaining rigorous guarantees.
New metric assesses reliability of AI explanations.
problem Unreliable AI explanations under realistic conditions.
method Explanation Reliability Index (ERI) metrics quantifying stability under four axioms.
result Widespread reliability failures in popular explanation methods.
Research tackles ML failure in non-similar data, introducing reliable algorithms.
problem Machine learning models fail in new data distributions.
method Formal definition, assumptions, and simple algorithms for reliable generalization.
result Introduction of algorithms providing more reliable generalization.
Bayesian learning improves reliability of molecular predictions for hit compound discovery.
problem Improving reliability of machine learning predictions for virtual screening.
method Bayesian learning algorithms applied to graph neural networks.
result Bayesian learning leads to well-calibrated predictions and higher hit compound success.
Synthetic experiments are crucial for assessing causal machine learning methods.
problem Current empirical evaluations of causal machine learning methods are insufficient and unreliable.
method Propose principles for conducting rigorous empirical analyses with synthetic data.
result Rigorous synthetic experiments are essential for building trust in causal machine learning methods.
Research tackles distribution shift issues in ML to improve AI reliability.
problem Distribution shift limits ML reliability and trustworthiness.
method Study three distribution shifts (perturbation, domain, modality) and investigate robustness, explainability, adaptability.
result Proposes effective solutions and fundamental insights for enhancing ML robustness, adaptability, and safety.
New framework uses conformal predictions for robust, scalable machine learning classification.
problem Developing robust and reliable machine learning models for classification.
method Introducing scalable classifiers linked to statistical order theory and probabilistic learning theory, defining a score function and conformal safety set.
result Demonstrated practical implications in cybersecurity for identifying DNS tunneling attacks.
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.
The fifth generation (5G) and beyond wireless networks are critical to support diverse vertical applications by connecting heterogeneous devices and machines, which directly increase vulnerability for various spoofing attacks. Conventional cryptographic and physical layer authentication techniques are facing some chall…
New framework bridges climate science and ML for easier climate model emulation.
problem High computational costs and mistrust of ML methods in climate models.
method Integrating climate science and machine learning perspectives to design easy-to-adopt emulators.
result Demonstrated reliability of emulators designed to address specific tasks.
A central machine is interested in estimating the underlying structure of a sparse Gaussian Graphical Model (GGM) from datasets distributed across multiple local machines. The local machines can communicate with the central machine through a wireless multiple access channel. In this paper, we are interested in designin…
Quantum model improves safety in machine learning.
problem Improving safety and robustness in machine learning models.
method Variational quantum classifier with amplitude encoding and SAFE-AI metrics.
result Quantum model provides competitive performance and improved robustness.
Study shows heavy-tailed distributions affect reliability of machine learning calibration statistics.
problem Reliability of calibration statistics for machine learning regression tasks is affected by heavy-tailed uncertainty and error distributions.
method Examined two calibration error estimation methods (CE and ZMS) and found ZMS to be less sensitive to heavy-tailed distributions.
result Heavy-tailed distributions make MSE and MV unreliable, but ZMS remains a reliable approach.
Study defines and optimizes bank reliability using LR and PSO.
problem Lack of reliability concept in financial services.
method Logistic Regression (LR) for initial estimation, Particle Swarm Optimization (PSO) for optimization.
result Optimal financial ratios maximize bank reliability.
The paper proposes an AI and IIoT framework for improved maintenance.
problem Current maintenance practices need improvement with AI and IIoT.
method Review of reliability modeling, introduction of Intelligent Maintenance framework, and novel probabilistic deep learning approach.
result Demonstrated novel probabilistic deep learning reliability modelling in Turbofan Engine Degradation Dataset.
Improves reliability of medical diagnosis uncertainty estimates.
problem Label uncertainty in medical diagnosis.
method Post-hoc alpha-calibration method for neural network classifiers. result Significantly enhances reliability of uncertainty estimates.
Study shows more data improves model explanations, aiding reliable knowledge extraction.
problem Challenges in deriving reliable knowledge from machine learning models due to the Rashōmon effect.
method Examined the influence of sample size on explanations from models in a Rashōmon set using SHAP.
result Explanations from <128 samples are highly variable, but agreement improves with more data.
The paper proposes a method to reliably select design algorithms for machine learning-guided design tasks.
problem Choosing the right design algorithm for machine learning-guided design tasks.
method Combining designs' predicted property values with held-out labeled data to reliably forecast characteristics of the label distributions produced by different design algorithms.
result The method is guaranteed to return design algorithms that yield successful label distributions.
QC methods improve reliability of machine learning-based image segmentation.
problem Inaccuracies in machine learning algorithms limit their clinical applicability.
method Analysis and validation of QC approaches for automatic segmentation.
result Aggregation of uncertainty and Dice prediction methods improved segmentation reliability.
New method uses interval-based metric to validate prediction uncertainty in machine learning.
problem Validation of prediction uncertainty in machine learning regression tasks is unreliable due to heavy-tailed distributions.
method Shift from variance-based metrics to interval-based Prediction Interval Coverage Probability (PICP).
result PICP method more quickly and reliably tests prediction intervals than variance-based metrics.
MLDemon monitors ML systems post-deployment, improving reliability with real-time performance estimates and expert labels.
problem Ensuring reliability of machine learning systems post-deployment, especially when user inputs differ from training data.
method Integrates unlabeled and on-demand labeled data to monitor ML model performance in real-time, deciding when to acquire expert labels.
result Outperforms existing approaches in temporal datasets with diverse distribution drifts, providing theoretical optimality for distribution drifts.
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator,…
NeurIPS 2019 program improves reproducibility in machine learning.
problem Ensuring machine learning research results are reproducible and reliable.
method Code submission policy, reproducibility challenge, and checklist integration.
result Improved reproducibility standards across the machine learning community.
With the advent of Deep Learning, the field of machine learning (ML) has surpassed human-level performance on diverse classification tasks. At the same time, there is a stark need to characterize and quantify reliability of a model's prediction on individual samples. This is especially true in application of such model…
The paper highlights the importance of model misspecification in uncertainty estimation.
problem The reliability of uncertainty estimates in machine learning models under model misspecification.
method Thought experiments and literature review.
result Model misspecification should be given more attention in uncertainty estimation.
Machine learning models provide statistically impressive results which might be individually unreliable. To provide reliability, we propose an Epistemic Classifier (EC) that can provide justification of its belief using support from the training dataset as well as quality of reconstruction. Our approach is based on mod…
Material scientists are increasingly adopting the use of machine learning (ML) for making potentially important decisions, such as, discovery, development, optimization, synthesis and characterization of materials. However, despite ML's impressive performance in commercial applications, several unique challenges exist …
This thesis enhances ML reliability by selectively abstaining from predictions when uncertain.
problem Improving reliability in machine learning systems, especially in high-stakes domains.
method Exploiting uncertainty signals from training trajectories to develop lightweight, post-hoc abstention methods compatible with differential privacy.
result A robust trajectory-based approach to selective prediction that maintains high accuracy under privacy noise.
Proposes standards for evaluating online machine learning methods in evolving data streams.
problem Difficulty in evaluating online machine learning methods under realistic conditions.
method Proposes comprehensive evaluation standards, performance measures, and evaluation strategies.
result Provides a new Python framework (float) for modular integration of libraries and custom code.
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development. Developing a machine learning model is no difference - it is an engineering process with a life cycle, including design, implementation, tuning, testing, and deploymen…
Paper tackles circularity issues in machine learning predictions.
problem Circularity problems in machine learning predictions.
method Not specified in the abstract.
result Not specified in the abstract.
The paper improves NN predictions with reliable confidence intervals.
problem Creating accurate prediction intervals for neural network outputs.
method Introduces Conformal Prediction (CP) for NNs, ensuring reliable confidence measures.
result The proposed method produces well-calibrated and tight prediction intervals.