Paper proposes a method to recover accurate labels from partially valid data in multi-label learning.
problem Tackles noisy supervision in multi-label learning with partially valid labels.
method Develops a two-stage method that estimates label enrichment and ground-truth confidences.
result Demonstrates improved performance over state-of-the-art PML methods.
DBLE improves confidence calibration of DNNs by learning distances in representation space.
problem Poor confidence calibration of deep neural networks (DNNs).
method DBLE trains a confidence model jointly with the classification model, using distances in the representation space.
result DBLE outperforms alternative single-model confidence calibration approaches and ensemble methods.
Algorithm identifies best arm with biased proxy and selective ground truth audits.
problem Fixed-confidence best-arm identification with biased proxy and selective ground truth.
method Propensity-weighted estimator and adaptive auditing algorithm.
result Plug-in Neyman rule achieves near-oracle audit efficiency.
New method improves model calibration by adjusting confidence based on prediction correctness.
problem Improving model confidence alignment with true class probabilities.
method Post-hoc calibration objective using transformed samples for training.
result Competitive calibration performance on in-distribution and out-of-distribution test sets.
PPI uses proxy data to improve inference from limited labels across related tasks.
problem Statistical inference with limited labels across multiple related tasks.
method Prediction-powered inference framework that uses cross-task recalibration to improve power and accuracy.
result Cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.
The paper introduces methods to quantify uncertainty in sampling without replacement.
problem Accurately estimating parameters from finite populations sampled without replacement.
method Develops confidence sequences using Bayesian and empirical methods.
result Improved confidence intervals and sequences for sampling without replacement.
A new framework evaluates LLMs by considering judge reliability.
problem Evaluating LLMs without ground truth labels can lead to biased results.
method Introduces judge-specific discrimination parameters and estimates model quality and judge reliability.
result Improves agreement with human preferences and produces calibrated uncertainty quantification.
PML-LFC improves PML by estimating label confidence from both feature and label spaces.
problem PML challenges in real-world scenarios where only some labels are relevant.
method PML-LFC estimates label confidence using feature and label space similarities, training a predictor with these values.
result PML-LFC achieves superior performance on synthetic and real-world datasets.
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between predictive uncertainty of networks and variance of the prediction scores obtained by …
Develops spatial uncertainty guarantees for image segmentation models.
problem Ensuring reliable segmentation predictions for biomedical images.
method Adapting conformal inference to imaging, using transformed logit scores and calibration datasets.
result Confidence sets provide spatial uncertainty guarantees with desired probability.
Pairwise Label Smoothing improves deep model generalization by reducing overconfidence.
problem Improving deep model generalization through regularization.
method PLS smooths labels for pairs of samples, learning distribution mass during training.
result PLS significantly outperforms LS and baseline models, reducing up to 30% classification error.
Audio source separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Deep learning models are the state-of-the-art in source separation, given that the mixture to be separated is similar to the mixtures the deep model was tr…
The paper addresses the difficulty of decision makers trusting AI-assisted predictions and proposes a method to improve confidence values.
problem Decision makers struggle to trust AI-assisted predictions based on confidence values.
method The paper investigates why decision makers have difficulties and proposes a method to construct more useful confidence values.
result Multicalibration with respect to the decision maker's confidence on her own predictions is a sufficient condition for alignment, leading to better decisions.
Researchers formalize PD and PFI to relate them to data generating process.
problem Lack of theory linking PD and PFI to data generating process.
method Formalize PD and PFI as estimators of ground truth estimands, account for model variance with learner-PD and learner-PFI.
result PD and PFI estimates deviate from ground truth due to statistical biases, model variance, and Monte Carlo approximation errors.
Improved AI lung ultrasound segmentation using expert confidence values.
problem Label uncertainty in lung ultrasound due to subjective interpretation by radiologists.
method Designing a data annotation protocol capturing expert confidence, training AI on binarized labels with confidence thresholds.
result Improved AI segmentation and better clinical outcomes (e.g., S/F oxygenation ratio estimation, patient readmission prediction).
Algorithm generates adaptive confidence sets for instance segmentation with guaranteed coverage.
problem Uncalibrated predictions and lack of uncertainty quantification in instance segmentation models.
method Conformal prediction algorithm to generate adaptive confidence sets with provable guarantees.
result Empirically, prediction sets vary in size based on query difficulty and attain target coverage, outperforming baselines.
Perry uses auxiliary data to estimate RL policy values with confidence intervals.
problem Leveraging auxiliary datasets for off-policy evaluation with uncertainty quantification.
method Two methods for constructing valid confidence intervals for OPE with data augmentation.
result Methods consistently produce confidence intervals covering ground truth policy values.
Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct. Most existing methods deal with such problem by either treating each candidate label equally or identifying the ground-truth label iteratively. In this pap…
New insights on active sequential prediction for mean estimation.
problem Active sequential prediction-powered mean estimation problem.
method Combining uncertainty-based suggestion with a constant probability, analyzing non-asymptotic bounds, and using no-regret learning.
result The optimal query probability is close to the constraint when using no-regret learning.
Study improves confidence measures in medical imaging pipelines by addressing bias.
problem Bias in metric-based imaging pipelines compromises the efficiency of prediction intervals.
method Formalized symmetric and asymmetric CP formulations, analyzed bias effects, and validated empirically.
result Symmetric intervals are inflated by bias, while asymmetric intervals remain unaffected.
Sensors which use electromagnetic induction (EMI) to excite a response in conducting bodies have long been investigated for subsurface explosive hazard detection. In particular, EMI sensors have been used to discriminate between different types of objects, and to detect objects with low metal content. One successful, p…
PPI uses predictions to improve inference from incomplete data.
problem Incomplete or costly-to-measure outcomes in research fields.
method Leverages large unlabeled datasets for improved statistical efficiency with bias correction.
result PPI variants produce tighter confidence intervals than complete-case analysis.
When forecasting time series with a hierarchical structure, the existing state of the art is to forecast each time series independently, and, in a post-treatment step, to reconcile the time series in a way that respects the hierarchy (Hyndman et al., 2011; Wickramasuriya et al., 2018). We propose a new loss function th…
B-REX efficiently learns Atari game policies from pixel inputs using Bayesian methods.
problem Learning reward functions from visual inputs with uncertainty and safety considerations.
method Bayesian Reward Extrapolation (B-REX) using successor features and preferences.
result B-REX generates posterior samples efficiently, enabling high-confidence performance bounds.
Proposes a weighted conformal approach for cluster label uncertainty.
problem Cluster label uncertainty in unlabeled data.
method Develops a conformal inference algorithm to correct label mismatch.
result Improves confidence set size in nonlinear and high-dimensional clustering.
In order to alleviate data sparsity and overfitting problems in maximum likelihood estimation (MLE) for sequence prediction tasks, we propose the Generative Bridging Network (GBN), in which a novel bridge module is introduced to assist the training of the sequence prediction model (the generator network). Unlike MLE di…
Paper proposes metrics to evaluate AI explanations without ground truth.
problem Challenges in evaluating neural network explanations without ground truth.
method Designs four metrics to evaluate explanation results.
result New insights into neural network interpretation methods.
TEAM generates more powerful adversarial examples for DNNs.
problem Vulnerability of DNNs to imperceptible adversarial examples.
method TEAM uses Taylor expansion and Lagrangian multiplier method to craft adversarial examples.
result TEAM generates adversarial examples with 100% attack success rate using smaller perturbations.
Universally valid ground truth is almost impossible to obtain or would come at a very high cost. For supervised learning without universally valid ground truth, a recommended approach is applying crowdsourcing: Gathering a large data set annotated by multiple individuals of varying possibly expertise levels and inferri…
Inference-Time Scaling can be extended to domains prone to systematic failure using intrinsic statistics.
problem Scaling inference time in domains prone to systematic failure
method Intrinsic Selection (iS), Intrinsic Particle Filtering (iPF), and Particle Distillation (dPF)
result Intrinsic Selection improves engineering design selection by 20% and pass@1 by 6.1 points on average.
Tests for classifier independence without ground truth labels.
problem Validation of classifier independence without ground truth labels.
method Exact solution for independent binary classifiers using algebraic geometry.
result Self-consistent test for classifier independence without ground truth labels.
RealCause provides a realistic benchmark for causal inference.
problem Lack of a reliable benchmark for comparing causal effect estimators.
method Flexible generative models to create a benchmark that is both ground-truth and realistic.
result Evaluation of over 1500 causal estimators provides evidence for choosing hyperparameters using predictive metrics.
For machine learning task, lacking sufficient samples mean the trained model has low confidence to approach the ground truth function. Until recently, after the generative adversarial networks (GAN) had been proposed, we see the hope of small samples data augmentation (DA) with realistic fake data, and many works valid…
PS-KD distills a model's own knowledge to soften hard targets during training.
problem Improving generalization of deep neural networks by softening hard targets.
method Progressive self-knowledge distillation (PS-KD) that progressively distills a model's own knowledge to soften hard targets.
result PS-KD improves accuracy and provides high quality of confidence estimates in terms of calibration and ordinal ranking.
Recently developed deep-learning-based denoisers often outperform state-of-the-art conventional denoisers such as the BM3D. They are typically trained to minimize the mean squared error (MSE) between the output image of a deep neural network (DNN) and a ground truth image. Thus, it is important for deep-learning-based …
Estimates classifier errors without ground truth using algebraic geometry.
problem Lack of ground truth in real-world production systems.
method Non-parametric estimation using algebraic geometry to solve the self-assessment problem.
result Accuracy estimators are better than one part in a hundred.
Ranking a set of objects involves establishing an order allowing for comparisons between any pair of objects in the set. Oftentimes, due to the unavailability of a ground truth of ranked orders, researchers resort to obtaining judgments from multiple annotators followed by inferring the ground truth based on the collec…
Paper introduces metrics to evaluate missing data imputation without ground truth.
problem Handling missing data in time series without ground truth.
method Introduces Wasserstein distance (WD) and Jensen-Shannon divergence (JSD) as metrics to evaluate imputation quality.
result WD and JSD are effective metrics for assessing missing data imputation quality.
Paper improves prediction sets for distribution shifts without labels.
problem Improving prediction sets effectiveness in the presence of distribution shifts.
method Develops ECP and EACP methods to adjust score function based on model uncertainty.
result Consistent improvement over existing baselines and nearly matches fully supervised methods.
Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with partially labeled examples. Specifically, we propose a unified formulation with pro…
A new score measures data reliability without ground truth.
problem Assessing reliability of datasets without access to ground truth.
method Define ground-truth-based orderings and propose Gram determinant score.
result Gram determinant score effectively captures data quality across diverse observation processes.
Preventing early progression of epilepsy and so the severity of seizures requires an effective diagnosis. Epileptic transients indicate the ability to develop seizures but humans overlook such brief events in an electroencephalogram (EEG) what compromises patient treatment. Traditionally, training of the EEG event dete…
QUACKIE creates a new benchmark for NLP interpretability.
problem Evaluating NLP interpretability methods is challenging due to biased ground truths.
method Formulated a custom classification task from question-answering datasets, generating unbiased ground truths.
result Demonstrated the effectiveness of current interpretability methods on the new benchmark.
Unsupervised clustering can reproduce categorization systems if features and metrics are correctly selected.
problem Reproducing expert-provided categorization systems using unsupervised clustering.
method Investigated using toy datasets and real-world fund categorization. Used appropriate feature selection and a supervised Random Forest-based distance metric.
result Unsupervised clustering can reproduce ground truth classes if features and metrics are correctly selected.
New method accounts for uncertainty in medical AI evaluations.
problem Uncertainty in ground truth affects AI model performance estimates.
method Statistical aggregation approach to infer probabilities of medical conditions.
result Performance estimates are significantly lower when uncertainty is accounted for.
Deep learning for Venus images uses high-res hyperspectral data to simulate ground truth.
problem Lack of accurate ground truth data for training deep neural networks in remote sensing.
method Unmixing high-resolution hyperspectral images to simulate ground truth for training a CNN.
result The model can classify mid-resolution Venus images successfully.
Automatic music transcription is considered to be one of the hardest problems in music information retrieval, yet recent deep learning approaches have achieved substantial improvements on transcription performance. These approaches commonly employ supervised learning models that predict various time-frequency represent…
Generative model combines multi-dimensional annotations for more accurate ground truth estimation.
problem Inaccurate ground truth estimation from naive annotators' multi-dimensional annotations.
method Proposes a joint multi-dimensional model for global and time-series annotation fusion using Expectation-Maximization algorithm.
result More accurate ground truth estimates through joint modeling of multiple dimensions.