analiza aiqbench
This paper is a machine learning research article: it extends neural diffusion processes with a task encoder for multi-task probabilistic regression and few-shot adaptation, and reports gains on synthetic and real-world data (wind turbines, school exam outcomes). The reported improvements are benchmarked against single-task diffusion, neural-process, and Gaussian-process baselines, so the practical claims are narrow and dataset-specific. For ML readers, the main takeaway is the design pattern of permutation-invariant task conditioning in generative regression models, with the calibration result in the wind application as the most relevant evidence.
Multi-task Neural Diffusion Processes
arXiv:2510.03419v3 Announce Type: replace-cross Abstract: Neural diffusion processes provide a scalable, non-Gaussian approach to modelling distributions over functions, but existing formulations are limited to single-task inference and do not capture dependencies across related tasks. We propose multi-task neural diffusion processes (MT-NDPs), an extension that incorporates a task encoder to enable task-conditioned probabilistic regression and few-shot adaptation across related functions. The task encoder extracts a low-dimensional representation from context observations and conditions the diffusion model on this representation, allowing information sharing across tasks while accommodating variable-sized context sets and preserving permutation invariance with respect to the ordering of context observations. We evaluate MT-NDPs through synthetic experiments and two real-world applications involving wind turbine data and school examination outcomes. The results demonstrate improved predictive accuracy relative to single-task diffusion baselines when context observations are available, alongside competitive performance against neural-process and Gaussian-process alternatives. In the wind-energy application, MT-NDPs achieve the lowest average coverage error among the evaluated models at larger context sizes, demonstrating improved predictive uncertainty calibration. Overall, our findings highlight the potential of task-conditioned diffusion models for uncertainty-aware multi-task regression and few-shot adaptation to previously unseen tasks.
Abstract:Neural diffusion processes provide a scalable, non-Gaussian approach to modelling distributions over functions, but existing formulations are limited to single-task inference and do not capture dependencies across related tasks. We propose multi-task neural diffusion processes (MT-NDPs), an extension that incorporates a task encoder to enable task-conditioned probabilistic regression and few-shot adaptation across related functions. The task encoder extracts a low-dimensional representation from context observations and conditions the diffusion model on this representation, allowing information sharing across tasks while accommodating variable-sized context sets and preserving permutation invariance with respect to the ordering of context observations. We evaluate MT-NDPs through synthetic experiments and two real-world applications involving wind turbine data and school examination outcomes. The results demonstrate improved predictive accuracy relative to single-task diffusion baselines when context observations are available, alongside competitive performance against neural-process and Gaussian-process alternatives. In the wind-energy application, MT-NDPs achieve the lowest average coverage error among the evaluated models at larger context sizes, demonstrating improved predictive uncertainty calibration. Overall, our findings highlight the potential of task-conditioned diffusion models for uncertainty-aware multi-task regression and few-shot adaptation to previously unseen tasks.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Applications (stat.AP); Machine Learning (stat.ML)
arXiv:2510.03419 [cs.LG]
(or arXiv:2510.03419v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2510.03419 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 281 cuvinte
Subiecte conexe
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026
Opaque recurrence, and other AI terms that you should probably know
TechCrunch · 7 sept. 2026
[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
Latent Space · 16 oct. 2026