Paper tackles learning time series models from noisy timestamps.
problem Learning time series detection models from temporally imprecise labels.
method Proposes a general learning framework accommodating different base classifiers and noise models.
result Significantly outperforms alternatives on real mobile health data.
DIR-ST2 delineates imprecise regions using spatio-temporal-textual data.
problem Finding precise boundaries of imprecise regions without clear boundaries.
method DIR-ST2 uses iterative DBSCAN clustering with spatio-temporal-textual information. result DIR-ST2 outperforms state-of-the-art methods in delineating imprecise regions. Two strategies extend multi-label chaining for imprecise probability estimates.
problem Handling imprecise probability estimates in multi-label classification.
method Adapting multi-label chaining to use convex sets of distributions (credal sets).
result Adapted approaches produce relevant cautiousness on hard-to-predict instances.
Model counts event occurrences to detect and locate events in data.
problem Training deep neural networks with precise event locations.
method Weakly-supervised learning using occurrence counts.
result Comparable performance to fully-supervised methods with weaker training data.
New methods detect targets from imprecisely labeled hyperspectral data.
problem Challenges in acquiring labeled hyperspectral data.
method Multi-Target MI-ACE and MI-SMF methods that learn target signatures from imprecisely labeled samples.
result Effective at learning target signatures and performing target detection.
Study on how imprecise medical data affects predictions in hyperthyroidism.
problem Impact of imprecise medical data on prediction results.
method Formulated a model for data imprecisions, generated imprecise samples, defined measures to evaluate impacts, and performed experiments.
result Small imprecisions can lead to large ranges of predicted results, potentially causing mis-labeling and inappropriate actions.
Paper improves conformal prediction for imprecise training data.
problem Applying conformal prediction to partially labeled data.
method Generalizes conformal prediction for set-valued training and calibration data.
result Validates the proposed method and shows it outperforms baselines.
Limited supervision can enable reliable disentangled representation learning.
problem Learning disentangled representations without inductive biases is theoretically impossible.
method Investigated the impact of limited supervision (0.01--0.5% of data) on disentanglement methods.
result A small number of labeled examples (0.01--0.5\% of the data set) is sufficient for model selection.
An imprecise SHAP method explains class probabilities with limited data.
problem Explaining class probabilities with limited training data.
method New approach for computing feature marginal contributions and general approach to interval-valued Shapley values.
result The imprecise SHAP method improves explanation of class probabilities.
Study enhances classifier robustness against noisy labels.
problem Impact of label noise on model performance in real-world scenarios.
method Integrates adversarial machine learning and importance reweighting techniques with CNN.
result Improved model resilience against noisy data.
This work introduces a new metric for comparing imprecise probability models.
problem Quantifying differences between imprecise probability models.
method Integral imprecise probability metric framework based on Choquet integral.
result IIPM enables comparison across different imprecise probability models and quantifies epistemic uncertainty.
Conformal Prediction Regions match Imprecise Highest Density Regions under consonance.
problem Matching conformal prediction regions with highest density regions.
method Using consonance and the Imprecise Probability theory of clouds.
result Imprecise Highest Density Regions are equivalent to Conformal Prediction Regions under consonance.
The paper analyzes when credal sets stabilize under iterative updates in machine learning.
problem When do credal sets stabilize under iterative updates in machine learning?
method Fixed-point theorems for credal set updates.
result The paper provides the first analysis of credal set stability.
New methods for handling time-varying label noise in time series classification.
problem Temporal label noise in time series classification tasks.
method Proposed methods to estimate temporal label noise function directly from data.
result Our methods lead to state-of-the-art performance under diverse types of temporal label noise.
Paper introduces novel survival models for handling censored data.
problem Complex data structures and heavy censoring in survival analysis.
method Combines imprecise probability theory with attention mechanisms.
result Proposed models, especially iSurvJ, outperform traditional methods.
Estimates transition rates of continuous-time Markov chains using imprecise probabilistic methods.
problem Estimating transition rate matrix from a finite-duration process.
method Imprecise probabilistic framework with conjugate priors and discrete-time analysis for hyperparameter determination.
result Continuous-time estimator with simple closed-form expression derived from discrete-time model.
Walley's Imprecise Dirichlet Model (IDM) for categorical i.i.d. data extends the classical Dirichlet model to a set of priors. It overcomes several fundamental problems which other approaches to uncertainty suffer from. Yet, to be useful in practice, one needs efficient ways for computing the imprecise=robust sets or i…
Study generalizes property elicitation to imprecise probabilities.
problem Minimizing risk over imprecise probability distributions.
method Maximin risk minimization over a set of imprecise probabilities.
result Conditions for elicitability of IP-properties.
We give an overview of two approaches to probability theory where lower and upper probabilities, rather than probabilities, are used: Walley's behavioural theory of imprecise probabilities, and Shafer and Vovk's game-theoretic account of probability. We show that the two theories are more closely related than would be …
Mean Teacher improves semi-supervised learning by averaging model weights, outperforming Temporal Ensembling.
problem Improving semi-supervised learning performance with limited labeled data.
method Averaging model weights instead of label predictions, penalizing inconsistency with an exponential moving average target.
result Mean Teacher achieves 4.35% error rate on SVHN with 250 labels, outperforming Temporal Ensembling with 1000 labels.
Paper introduces imprecise logistic regression for handling uncertain data.
problem Uncertainties in data prevent traditional logistic regression from being applied effectively.
method Develops imprecise logistic regression model using intervals of possible values.
result Clearly expresses epistemic uncertainty in predictions.
New method uses conformalization to create classification regions from ambiguous labels.
problem Creating provable guarantees in classification with uncertain labels.
method Conformal methods applied to credal regions for classification problems.
result New method provides smaller and more disentangled prediction sets.
Labels define the effective timescale for learning from short observations.
problem Learning from short observations with aggregated labels.
method Analytical and Monte Carlo methods to study label variance and effective timescales.
result Labels define the effective timescale for learning, distinguishing architectural from protocol limits.
The study establishes stability in WMOT, crucial for finance with imprecise data.
problem Stability in weak martingale optimal transport for finance with imprecise data.
method Established stability through rigorous mathematical analysis.
result Stability of WMOT is proven, with applications to VIX futures and Brownian motion.
CTCModel extends Keras for transparent CTC classification.
problem Handling unsegmented input sequences with labels related to subsets of frames.
method Combines Keras and CTC implementation in Tensorflow backend.
result CTCModel predicts sequences of labels from unsegmented input.
TCR improves DNN robustness to noisy labels with minimal overhead.
problem Training on noisy labeled datasets degrades DNN generalization.
method TCR combines original labels and previous epoch predictions for regularization.
result TCR consistently enhances DNN robustness to label noise.
Optimizes trading strategy for cointegrated assets with bounded risk.
problem Maximizing profit from cointegrated assets with risk constraints.
method Formulates as convex optimization problem, then generalizes to bounded risk.
result Optimal strategy remains efficiently solvable even with bounded risk.
Develops STC for sequential data with missing labels.
problem Learning from partially labeled and unsegmented sequential data.
method Introduces Star Temporal Classification (STC) using a star token and GTN framework.
result Recover most of supervised baseline performance with up to 70% missing labels.
We introduce imprecise Markov semigroups to handle uncertainty in Markov processes.
problem Uncertainty in transition probabilities and invariant measures of Markov processes.
method Topology, geometry, and probability techniques to analyze ergodic limits under model uncertainty.
result Uniform long-term bounds collapse asymptotically in certain regimes.
New tools connect CP to GF inference for better probabilistic prediction.
problem Lack of versatility in conformal prediction for quantifying evidence.
method Imprecise probability theory and generalized fiducial inference.
result Establishes a formal connection between CP and GF inference.
This paper explores semi-qualitative probabilistic networks (SQPNs) that combine numeric and qualitative information. We first show that exact inferences with SQPNs are NPPP-Complete. We then show that existing qualitative relations in SQPNs (plus probabilistic logic and imprecise assessments) can be dealt effectively …
Method learns node embeddings over time for graph prediction tasks.
problem Predicting links and classifying nodes in evolving graphs.
method Proposes a joint loss function for temporal node embedding.
result Improves performance on various temporal graph tasks.
New method predicts RUL and failure modes from partial data.
problem Predicting RUL and failure modes from incomplete data.
method Formulated as vector General Value Function (GVF) prediction on an absorbing degradation process, using TD(n,λ) for estimation. result TD improves RUL and failure-mode prediction compared to Monte Carlo methods, especially under scarce complete labels.
Proposes interpretable attention for video action recognition.
problem Efficient video action recognition with attention mechanisms.
method Spatial-temporal attention mechanism with saliency masks and convolutional LSTM.
result Improves video action recognition accuracy and spatial-temporal localization.
Bayesian method improves deep learning for noisy EEG seizure detection.
problem Label noise in scalp EEG data hinders deep learning performance.
method Integrates domain knowledge into a Bayesian framework to inform deep learning models of label ambiguities.
result BUNDL enhances robustness of seizure detection systems under noisy label conditions.
Researchers develop a new method to learn from incomplete data.
problem Learning from incomplete data with imprecise probabilities.
method Credal sum-product networks (SPNs) for robust probabilistic representations.
result Imprecise SPNs can capture robustness to missing data.
MILCCI integrates labels across categories for better understanding of multi-trial data.
problem Understanding how labels encode multi-trial observations and disentangling their effects.
method Sparse per-trial decomposition leveraging label similarities within each category.
result MILCCI identifies interpretable components and integrates label information.
STAD adapts models to evolving time-based data shifts.
problem Gradual distribution shifts over time challenge existing test-time adaptation methods.
method Bayesian filtering method that learns time-varying dynamics in hidden features.
result STAD excels in handling small batch sizes and label shift on real-world data.
New method achieves faster calibration without randomization.
problem Calibrating probabilistic forecasts in adversarial settings.
method Using interval forecasts and the power of two choices.
result Achieves O(1/T) calibration error rate without randomization. TNC learns time series representations by leveraging temporal neighborhoods.
problem Complex, unlabeled time series data.
method Temporal Neighborhood Coding (TNC) with a debiased contrastive objective.
result TNC outperforms other unsupervised methods in time series clustering and classification.
Study on how intraclass variability affects Temporal Ensembling accuracy.
problem Effect of intraclass variability on Temporal Ensembling accuracy.
method Investigated through experiments with varying seed sizes and types on different datasets.
result Significant drop in accuracy with high intraclass variability datasets, more seed images improve accuracy, and seed type impacts overall efficiency.
DTC learns time series clusters without labels.
problem Unsupervised learning of time series data.
method Deep Temporal Clustering (DTC) integrates autoencoder for dimensionality reduction and a novel temporal clustering layer.
result DTC outperforms traditional methods in various domains.
The study creates user personas based on user tenure and behavior for VoD streaming.
problem Understanding evolving user behavior in streaming services without explicit user profiles.
method Construct user personas using tenure timelines and temporal behavioral features.
result Personas provide stable and interpretable insights into user behavior evolution.
CT-OT Flow estimates continuous-time dynamics from discrete snapshots.
problem Estimating continuous-time dynamics from temporally aggregated snapshots with noisy or uncertain timestamps.
method Two-stage framework: aligning neighboring intervals via partial optimal transport (POT) and reconstructing a continuous-time distribution through temporal kernel smoothing.
result Reduces distributional and trajectory errors compared with existing methods across synthetic and real datasets.
We develop a new statistical test for comparing variables with varying scales.
problem Comparing variables with different scales in multidimensional spaces.
method Order based on expectations of random variables, generalized stochastic dominance (GSD) order, regularized statistical test, linear optimization, imprecise probability models.
result Validated through multidimensional data from various fields.
Develops a deep generative model for radar target recognition using HRRP data.
problem Automatic target recognition in radar systems using high-resolution range profiles.
method Recurrent gamma belief network (rGBN) with hybrid stochastic-gradient MCMC and variational inference.
result Efficient and accurate classification with interpretable latent structure.
New approach for handling uncertain probabilities.
problem Handling imprecise or uncertain probabilities.
method Introducing interval probability measures and updating rules.
result Formal solution to the Keynes-Ramsey controversy.
A method for predicting credal sets in classification tasks using conformal prediction.
problem Designing methods for learning credal set predictors in machine learning.
method Incorporates conformal prediction for predicting credal sets in classification tasks.
result Conformal credal sets are guaranteed to be valid with high probability.