Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

130260390520 · Jun 202019922001200920172026
48 results for out-of-distribution prediction

Combining Bayesian deep learning and split conformal prediction affects out-of-distribution coverage.

problem Improving out-of-distribution coverage in multiclass image classification.
method Combining Bayesian deep learning with split conformal prediction methods.
result Combining methods can reduce out-of-distribution coverage in some cases.

New methods predict language model out-of-distribution behaviors using causal mechanisms.

problem Predicting how language models behave on unseen data.
method Two methods: counterfactual simulation and value probing.
result Both methods achieve high AUC-ROC and outperform causal-agnostic approaches in out-of-distribution settings.

Study optimal ridge regularization for out-of-distribution prediction.

problem Optimal ridge regularization for predicting out-of-distribution data.
method Established conditions for optimal regularization under covariate and regression shifts, proving monotonic risk in data aspect ratio.
result Negative regularization can be optimal under shifts, even with isotropic or underparameterized training features.

Proposes training neural networks to predict uncertainty for out-of-distribution inputs.

problem Poor uncertainty predictions for out-of-distribution inputs limit model robustness.
method Generates pseudo-inputs in low-density regions and trains a Bayesian framework.
result Yields robust and interpretable uncertainty predictions.

A simple method flags images as out-of-distribution based on their distance to nearest neighbors.

problem Detecting images not aligned with a trained model's in-distribution data.
method Flag images as OOD if their average distance to K nearest neighbors is large in the classifier's representation space.
result Simple methods can outperform more complex ones when considering learned representations.

A new metric predicts model performance on unseen data.

problem Predicting performance on out-of-distribution data without labels.
method Uses model predictions to pseudo-label data, trains a new model, and measures difference from in-distribution models.
result Empirically outperforms existing methods on image and text classification tasks.

Deep learning models are known to be overconfident in their predictions on out of distribution inputs. This is a challenge when a model is trained on a particular input dataset, but receives out of sample data when deployed in practice. Recently, there has been work on building classifiers that are robust to out of dis…

2018-12-01abs ↗pdf ↗

GCRL learns causal factors for motion forecasting, improving out-of-distribution prediction.

problem Sensitivity to out-of-distribution data in conventional supervised learning methods.
method Generative Causal Representation Learning (GCRL) leveraging causality for knowledge transfer.
result Significantly outperforms prior models on out-of-distribution prediction.

Bayesian Gaussian Processes layer detects out-of-distribution data in medical imaging.

problem Detecting out-of-distribution data in medical imaging tasks.
method Parameter-efficient hierarchical convolutional Gaussian Processes in Wasserstein-2 space.
result Uncertainty estimates enable superior out-of-distribution detection compared to previous methods.

PostNet predicts uncertainty without OOD data, improving OOD detection and calibration.

problem Accurate uncertainty estimation for safe systems.
method PostNet uses Normalizing Flows to learn individual posterior distributions over predicted probabilities.
result PostNet achieves state-of-the-art results in OOD detection and uncertainty calibration.

Proposes CSG model to separate semantic and variation factors for OOD prediction.

problem Out-of-distribution examples cause conventional models to mix semantic and variation factors, leading to poor performance.
method Causal Semantic Generative model (CSG) based on causal reasoning, using variational Bayes for efficient learning and prediction.
result CSG can identify semantic factor and improve OOD prediction performance.

Bayesian deep learning improves out-of-distribution detection but not always.

problem Improving the reliability of deep learning models in uncertain or novel data.
method Validation of likelihood-based Bayesian models for out-of-distribution detection.
result Bayesian deep learning models can marginally outperform conventional neural networks in certain conditions.

Improves uncertainty estimation and OOD detection in neural networks.

problem Accurate uncertainty estimation and OOD detection in neural networks.
method Investigates one-vs-all and distance-based logit representations for probabilities.
result One-vs-all formulations improve calibration without additional complexity.

We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks. In particular, MFVI fails to give calibrated uncertainty estimates in between separated regions of observations. Th…

2019-06-27abs ↗pdf ↗

Paper decomposes risk into aleatoric and epistemic uncertainties and generates predictive uncertainty measures.

problem Unclear relationships between various predictive uncertainty measures in literature.
method Bayesian estimation to decompose risk into aleatoric and epistemic uncertainties, generating different predictive uncertainty measures.
result Experimental validation confirms usefulness of derived predictive uncertainty measures for detecting out-of-distribution and misclassified instances.

p-DkNN uses deep representations to detect out-of-distribution data with statistical tests.

problem Lack of reliable confidence estimates in neural networks for safety-critical applications.
method Statistical testing of deep neural network's intermediate hidden representations.
result p-DkNN enables more accurate and reliable predictions by abstaining from incorrect predictions.

Work proposes a new framework to improve uncertainty estimation in deep Bayesian models.

problem Traditional training procedures underestimate uncertainty in NLMs, leading to unreliable predictions.
method Introduces a novel training framework that captures useful predictive uncertainties for out-of-distribution inputs.
result Demonstrates that traditional methods for NLMs significantly underestimate uncertainty and propose a new framework to address this issue.

SLUG method detects bias and out-of-distribution content in generative models.

problem Generative models can underrepresent certain groups and fail on out-of-distribution data.
method SLUG: A new uncertainty quantification method for VAEs combining Laplace approximations and stochastic trace estimators.
result SLUG's UQ score correlates with bias and out-of-distribution content.

New method detects uncertainty in neural networks for out-of-distribution detection.

problem Detecting out-of-distribution inputs to ensure model reliability.
method Predictive topological uncertainty (pTU) based on persistent homology.
result pTU provides a statistical framework for OOD detection.

In-N-Out improves model robustness to out-of-distribution data.

problem Learning robust models with few in-distribution labeled examples.
method Pre-training with auxiliary information and self-training with pseudolabels.
result In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.

A new method ranks uncertainty vectors from multiple measures for robust prediction.

problem Single scalar measures of model reliability are insufficient for comprehensive uncertainty quantification.
method Optimal transport ranks vectors of uncertainty measures, supporting flexible fusion of aleatoric and epistemic uncertainties.
result The method provides a robust ranking of uncertainty that supports various downstream tasks.

Bayesian autoencoder detects AI safety risk of out-of-distribution inputs.

problem Detecting unreliable predictions from AI models with different distributions.
method Probabilistic, unsupervised Bayesian variational autoencoder with posterior estimation.
result Effective detection of out-of-distribution inputs in both input and latent spaces.

Paper fine-tunes a simulation-driven estimator to reduce out-of-distribution errors.

problem Out-of-distribution errors in simulation-driven parameter estimators.
method Fine-tuning a Two-Stage estimator to improve accuracy for true parameters outside the sampled range.
result The fine-tuning approach reduces out-of-distribution errors and improves accuracy.

New framework detects out-of-distribution samples efficiently.

problem Detecting samples from different distributions in deep neural networks.
method Statistical hypothesis testing framework combining evidence from entire network.
result Framework maintains Type I Error and achieves comparable results to state-of-the-art methods.

This work proposes using Conformal Prediction to improve OOD detection scores and vice versa.

problem Improper evaluation of OOD detection scores due to finite sample size.
method Defining new conformal AUROC and FRP@TPR95 metrics and using OOD scores as non-conformity scores.
result Improved evaluation metrics and better interpretation of OOD scores.

Study shows gMPNNs struggle with OOD link prediction in larger test graphs.

problem Inductive out-of-distribution link prediction in larger test graphs.
method Theoretical analysis and development of a gMPNN with structural pairwise embeddings.
result Structural node embeddings from gMPNNs converge to random guessing as test graphs grow.

A new operator based on t-distributions improves NN classifiers' robustness to out-of-distribution samples.

problem NN classifiers assign extreme probabilities to out-of-distribution samples, leading to unreliable predictions.
method Derive a novel operator using t-distributions to model uncertainty more accurately.
result Classifiers using the new operator are more robust to out-of-distribution samples.

GGA improves untrustworthy prediction detection in neural networks without retraining.

problem Susceptibility of neural networks to untrustworthy predictions, especially adversarial attacks and out-of-distribution data.
method Geometric Gradient Analysis (GGA) analyzes the geometry of neural network loss landscapes based on saliency maps.
result GGA outperforms existing methods in detecting untrustworthy predictions, including adversarial and out-of-distribution data.

Real-time detection of out-of-distribution data in CPS control systems.

problem Detecting out-of-distribution data in CPS control systems for safety.
method Inductive conformal prediction and anomaly detection using variational autoencoders and deep support vector data description.
result Efficient real-time detection with low false alarm rates and comparable execution time.

Transformers encode latent distributions in text, improving performance in out-of-distribution cases.

problem What should embeddings from language models represent?
method Connecting autoregressive prediction to sufficient statistics, identifying three settings.
result Transformers encode latent generating distributions, improving performance.

The paper proposes a framework for information-theoretic predictive uncertainty measures.

problem The need for reliable estimation of predictive uncertainty in machine learning.
method Revisiting core concepts, categorizing predictive uncertainty measures based on model and approximation of true distribution.
result Identification of conditions under which certain predictive uncertainty measures excel.

Survey connects three DNN generalization fields for better inference.

problem Assessing if DNNs generalize correctly at inference time.
method Investigates predictive uncertainty, out-of-distribution, and adversarial example detection.
result Connects three fields for better DNN inference.