Image de couverture de livre

Forecasting the Past: Gradient-Based Distribution Shift Detection in Trajectory Prediction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	De Vita, Michele, Wiederer, Julian, Belagiannis, Vasileios
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation
par: De Vita, Michele, et autres
Publié: (2024)

Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
par: Asthana, Rohan, et autres
Publié: (2026)

GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection
par: Yang, Yutong, et autres
Publié: (2026)

LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation
par: Karimov, Mirlan, et autres
Publié: (2026)

CUQDS: Conformal Uncertainty Quantification under Distribution Shift for Trajectory Prediction
par: Huang, Huiqun, et autres
Publié: (2024)

Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
par: Jaziri, Achref, et autres
Publié: (2025)

Multi-conditioned Graph Diffusion for Neural Architecture Search
par: Asthana, Rohan, et autres
Publié: (2024)

Online Distribution Shift Detection via Recency Prediction
par: Luo, Rachel, et autres
Publié: (2022)

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
par: Chen, Mouxiang, et autres
Publié: (2023)

Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
par: Hoang, Dung Anh, et autres
Publié: (2022)

Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
par: Xie, Renchunzi, et autres
Publié: (2024)

The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning
par: Fröhlich, Johanna S., et autres
Publié: (2026)

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
par: Hu, Yifan, et autres
Publié: (2025)

Epistemic Errors of Imperfect Multitask Learners When Distributions Shift
par: Sloman, Sabina J., et autres
Publié: (2025)

Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting
par: Shu, Yuxuan, et autres
Publié: (2025)

MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting
par: Lehocine, Mohammed Amine Bencheikh, et autres
Publié: (2026)

Distribution Shift Is Key to Learning Invariant Prediction
par: Zheng, Hong, et autres
Publié: (2026)

Path-Based Gradient Boosting for Graph-Level Prediction
par: Meggio, Claudio, et autres
Publié: (2026)

DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting
par: Shu, Yuxuan, et autres
Publié: (2024)

Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts
par: Qin, Dalin, et autres
Publié: (2024)

APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift
par: Li, Yujie, et autres
Publié: (2025)

Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection
par: Hölle, Marc, et autres
Publié: (2025)

Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts
par: Zhang, Guangyi, et autres
Publié: (2026)

Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt
par: Zhang, YiFan, et autres
Publié: (2024)

Adapting Prediction Sets to Distribution Shifts Without Labels
par: Kasa, Kevin, et autres
Publié: (2024)

DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
par: Wood, Kieran, et autres
Publié: (2026)

Performative Prediction: Past and Future
par: Hardt, Moritz, et autres
Publié: (2023)

Wasserstein-regularized Conformal Prediction under General Distribution Shift
par: Xu, Rui, et autres
Publié: (2025)

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
par: Sun, Yanru, et autres
Publié: (2024)

Conformal Predictive Distributions for Order Fulfillment Time Forecasting
par: Ye, Tinghan, et autres
Publié: (2025)

LTAU-FF: Loss Trajectory Analysis for Uncertainty in Atomistic Force Fields
par: Vita, Joshua A., et autres
Publié: (2024)

Robust Validation: Confident Predictions Even When Distributions Shift
par: Cauchois, Maxime, et autres
Publié: (2020)

Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts
par: Dong, Yuze, et autres
Publié: (2026)

Conformalized Adaptive Forecasting of Heterogeneous Trajectories
par: Zhou, Yanfei, et autres
Publié: (2024)

Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs
par: Xu, Xiaoyang, et autres
Publié: (2025)

AIS-LLM: A Unified Framework for Maritime Trajectory Prediction, Anomaly Detection, and Collision Risk Assessment with Explainable Forecasting
par: Park, Hyobin, et autres
Publié: (2025)

Alleviating Structural Distribution Shift in Graph Anomaly Detection
par: Gao, Yuan, et autres
Publié: (2024)

Benchmarking Distribution Shift in Tabular Data with TableShift
par: Gardner, Josh, et autres
Publié: (2023)

Predicting the Future by Retrieving the Past
par: Du, Dazhao, et autres
Publié: (2025)

Robust Calibration For Improved Weather Prediction Under Distributional Shift
par: Gilda, Sankalp, et autres
Publié: (2024)