ReLU networks often give high confidence far from training data, new technique mitigates this.
problem ReLU networks produce high confidence predictions far from training data, which is undesirable.
method Proposed a new robust optimization technique similar to adversarial training to enforce low confidence predictions.
result The technique reduces confidence of predictions far from training data while maintaining test error on the original task.
New method provides reliable high-confidence prediction intervals for high-impact events.
problem High-impact events require very high confidence prediction intervals, but classical methods provide uninformative intervals.
method Bridge extreme value statistics and conformal prediction to provide reliable and informative prediction intervals.
result Provides reliable and informative prediction intervals with high-confidence coverage.
A new method for predicting with confidence for complex models.
problem Lack of reliable confidence in high-stake decision-making models.
method Developed a full-CP for sparse high-order interaction model using homotopy mining.
result SHIM achieves comparable accuracy to complex models and superior statistical power.
Paper defines and solves a problem in representation learning to ensure fairness with high confidence.
problem Learning fair representations with high confidence guarantees for all downstream tasks.
method Formally defines the problem, introduces FRG framework, proves high probability fairness, and demonstrates effectiveness empirically.
result FRG framework provides high-confidence guarantees for limiting unfairness across all downstream models and tasks.
Algorithm constructs confidence sets for deep neural networks with PAC guarantees.
problem Ensuring reliable predictions for deep neural networks with high confidence.
method Combines calibrated prediction and learning theory bounds.
result Constructs PAC confidence sets for various deep models.
Confidence-based filtering reveals latent structure in diffusion models.
problem Unclear latent structure in diffusion models.
method Confidence scores from a classifier.
result Class-relevant latent structure emerges under confidence-based filtering.
Waldo method constructs valid confidence regions for simulator-based inference.
problem Constructing valid confidence regions for simulator-based inference with high-dimensional data.
method Reframes Wald test statistic and uses regression-based machinery for Neyman inversion.
result Waldo method produces conditionally valid and precise confidence regions.
Paper proposes sparse classification method for high-dimensional data.
problem Sparse classification in high-dimensional data with positive-confidence samples.
method Developed a novel sparse-penalization framework using L1, SCAD, and MCP penalties for convex and non-convex shrinkage.
result Proved near minimax-optimal sparse recovery rates under Restricted Strong Convexity condition.
New method predicts sets under unknown covariate shift with high confidence.
problem Adapting to unknown covariate shift in prediction sets.
method PredSet-1Step, a flexible distribution-free method.
result Achieves asymptotic probably approximately correct coverage.
Mutual teaching improves graph models with less labeled data.
problem Training graph models with limited labeled data.
method Dual model training with mutual teaching strategy.
result Significant performance improvement with less labeled data.
This paper introduces a new method for uncertainty quantification in prediction models.
problem Quantifying uncertainty in high-stakes applications like medicine and finance.
method Confidence sets for outcome excursions, focusing on identifying subsets of features where outcomes exceed a threshold.
result Theoretical guarantees for the probability that confidence sets contain the true feature subset, both asymptotically and for finite sample sizes.
Develops a method to find costly high-confidence errors in black box models.
problem Finding rare high-confidence errors missed by random sampling.
method Adversarial perturbation-guided search technique to find errors at rates greater than expected given model confidence.
result Our Adversarial Distance search discovers high-confidence errors at a rate greater than expected given model confidence.
ICP provides interval predictions with high confidence coverage.
problem High-risk settings where true output must be highly probable.
method ICP is a distribution-free, model-agnostic algorithm.
result ICP outputs prediction intervals with high coverage probability.
This paper improves deep learning classifiers by integrating conformal prediction during training.
problem High-stake AI applications require reliable uncertainty estimates for safe deployment.
method Integrates conformal prediction (CP) during training of deep learning models.
result Reduces inefficiency and allows more control over confidence sets.
Novel U-learning method for predicting continuous outcomes from high-dimensional data.
problem Challenges in making valid inferences on predictions from high-dimensional inputs.
method U-learning via combinatory multi-subsampling for ensemble predictions and confidence intervals.
result Valid inferences on predictions from Lasso and neural networks.
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.
New method improves certified robustness for classifier confidence.
problem Certifying confidence in classifier predictions.
method Randomized smoothing with modified Neyman-Pearson lemma.
result Certified radii for prediction confidence improved.
It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to adversarial examples. This work is one of the most proactive approaches taken to date, as…
Deep learning reveals ubiquitous predictability in high-frequency returns.
problem Predicting returns in order book markets at high frequencies.
method Volume representation of the order book, deep learning models, model confidence sets.
result Predictability in mid-price returns is ubiquitous at high frequencies.
New method for accurate uncertainty estimation in deep learning predictions.
problem Insufficient methods for assessing prediction uncertainty in deep learning.
method Valid non-parametric bootstrap method for deep neural networks.
result Accurate confidence intervals and simultaneous confidence bands for survival data.
The paper studies how more data affects prediction risk in high-dimensional models.
problem The impact of increasing data on prediction risk in high-dimensional models.
method Derives central limit theorem and provides finite-sample distribution and confidence interval for prediction risk.
result Demonstrates 'more data hurt' phenomenon in high-dimensional least squares estimation.
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.
CCE improves anomaly detection metrics by measuring both confidence and consistency.
problem Existing anomaly detection metrics lack discriminative power, hyperparameter dependency, and robustness to perturbations.
method CCE uses Bayesian estimation to quantify uncertainty and constructs global and event-level confidence and consistency scores.
result CCE demonstrates strict boundedness, robustness, and linear time complexity.
New method constructs confidence sets for GLMs via game theory.
problem Developing reliable confidence intervals for GLM parameters.
method Reduction to sequential prediction games with low regret.
result Online-to-confidence-set conversions provide new types of intervals.
Ensembling multiple predictions is a widely used technique for improving the accuracy of various machine learning tasks. One obvious drawback of ensembling is its higher execution cost during inference. In this paper, we first describe our insights on the relationship between the probability of prediction and the effec…
New attacks can infer model training membership using only label predictions, not confidence.
problem Inferring whether a data point was used to train a machine learning model.
method Evaluate model's predicted labels under perturbations to infer membership.
result Label-only attacks perform as well as confidence-based attacks and break defenses that rely on confidence masking.
Paper tackles fooling deep networks with minimal perturbations.
problem Easily fooling deep neural networks with high confidence predictions.
method Uses integrated adaptive gradients to generate minimal adversarial perturbations.
result Achieves minimal adversarial perturbations for fooling deep networks.
Discriminative jackknife estimates deep learning uncertainty.
problem Quantifying uncertainty in deep learning models.
method Discriminative jackknife using influence functions of loss.
result DJ satisfies frequentist coverage and discriminative accuracy.
A new classifier method detects out-of-distribution samples by minimizing KL divergence.
problem Detecting out-of-distribution samples in neural networks.
method Training a confident-classifier by minimizing KL divergence and maximizing entropy, or adding a reject class.
result The confident-classifier still yields high confidence for OOD samples far from the in-distribution.
Meta-learned confidence improves few-shot learning accuracy.
problem Improving accuracy in few-shot learning with unreliable model confidence.
method Meta-learning confidence weights for query samples to improve transductive inference performance.
result Meta-learned confidence leads to new state-of-the-art results on benchmark datasets.
DeepLR constructs confidence intervals for neural networks with asymmetric expansions.
problem Uncertainty estimation for neural network predictions.
method Likelihood-ratio-based approach for constructing asymmetric confidence intervals.
result DeepLR offers asymmetric intervals expanding in regions with limited data.
This research improves model interpretability and uncertainty estimation for deep learning models on non-iid data.
problem Improving interpretability and uncertainty estimation for deep learning models on non-iid data.
method 4 UQ approaches (BNN, SWAG, MC dropout, ensemble) applied to ARMED MEDL models.
result Ensemble approaches, especially with 90% subsampling, provide best performance in prediction and uncertainty estimation.
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.
Bayesian approach calibrates DNN confidence for field use.
problem DNN models give false predictions with high confidence in real-world applications.
method Bayesian approach using Gaussian Process Regression to correct confidence with minimal labeled operation data.
result Significantly reduces high-confidence errors with minimal labeled data.
Confidential Guardian prevents model abstention from being used to discriminate.
problem Dishonest institutions can exploit machine learning model abstention to unfairly deny services.
method Confidential Guardian uses zero-knowledge proofs to verify model confidence and detect suppression.
result Confidential Guardian effectively prevents the misuse of cautious predictions.
This paper improves surrogate modeling for noisy data.
problem Uncertainty in high-fidelity models due to noise.
method Comprehensive framework for multi-fidelity surrogate modeling.
result Estimates uncertainty in high-fidelity model predictions.
We consider the setting of linear regression in high dimension. We focus on the problem of constructing adaptive and honest confidence sets for the sparse parameter θ, i.e. we want to construct a confidence set for theta that contains theta with high probability, and that is as small as possible. The l_2 diameter of a …
The paper finds a fundamental trade-off between confidence and efficiency in transductive conformal prediction.
problem The challenge is to balance confidence and efficiency in predicting multiple data points.
method The authors derive a strict finite-sample bound and introduce a practical algorithm to approach this bound.
result Any non-trivial confidence level leads to exponential growth in prediction set size, with a linear scaling in the number of samples.
Bayesian sequence prediction is a simple technique for predicting future symbols sampled from an unknown measure on infinite sequences over a countable alphabet. While strong bounds on the expected cumulative error are known, there are only limited results on the distribution of this error. We prove tight high-probabil…
Bayes-TrEx finds in-distribution examples for model inspection.
problem Challenges in interpreting neural networks, especially high-confidence failures and ambiguous classifications.
method Bayesian sampling approach to find in-distribution examples with specified prediction confidence.
result Bayes-TrEx enables more flexible holistic model analysis than just inspecting the test set.
Estimates prediction uncertainty in neural networks using density estimation in representation space.
problem Incorrect predictions with high confidence from models trained on limited data.
method Estimates training data density in representation space and uses it to predict model uncertainty.
result Detects out-of-distribution data without prior exposure, improving model reliability.
UnKGCP generates prediction intervals for uncertain knowledge graphs with statistical guarantees.
problem Lack of quantified predictive uncertainty in existing UnKGE methods.
method Proposes extsc{UnKGCP} framework using conformal prediction with a novel nonconformity measure.
result Sharp prediction intervals effectively capture predictive uncertainty in diverse UnKGE methods.
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.
The paper shows over-confidence in models isn't just due to over-parametrization.
problem Over-confidence in machine learning models, especially in binary classification.
method Theoretical analysis of logistic regression and other binary classification problems.
result Logistic regression is inherently over-confident in certain settings, but over-confidence is not always the case.
Introduces CCR for constructing confidence regions from conformal predictions.
problem Challenges in constructing confidence regions for model parameters.
method Combines conformal prediction intervals for model outputs to establish confidence regions for parameters under minimal assumptions.
result Valid coverage guarantees for finite sample regime, applicable to various model types.
Selective prediction framework reduces errors in molecular structure identification from MS/MS.
problem High-stakes applications require reliable molecular structure identification from MS/MS data.
method Selective prediction framework using risk-coverage tradeoff and uncertainty quantification.
result First-order confidence measures and retrieval-level aleatoric uncertainty achieve strong risk-coverage tradeoffs.
PaRCE estimates model confidence for CNNs across various uncertainties.
problem Limited holistic approach to estimating perception model confidence in CNNs.
method Probabilistic and reconstruction-based competency estimation.
result PaRCE best distinguishes between various types of samples and regions.
Deep learning architectures have proved versatile in a number of drug discovery applications, including the modelling of in vitro compound activity. While controlling for prediction confidence is essential to increase the trust, interpretability and usefulness of virtual screening models in drug discovery, techniques t…