analiza aiqbench
This research introduces the HOLMES model, a novel computational framework that enables trial-by-trial inference of hierarchical latent structures without explicit supervision. By combining nested priors with sequential Monte Carlo methods, it achieves compact representations capable of one-shot backward transfer and robust prediction for unseen feature combinations in sequential data. The work advances machine learning theory by bridging the gap between flat online models and complex offline Bayesian approaches through tractable multiscale inference.
Hierarchical Latent Structure Learning through Online Inference
arXiv:2603.19139v2 Announce Type: replace Abstract: Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires representations that support both. Online latent-cause models support incremental inference but assume flat partitions, whereas hierarchical Bayesian models capture multilevel structure but typically require offline inference. We introduce the \textbf{Hierarchical Online Learning of Multiscale Experience Structure (HOLMES) model}, a computational framework for hierarchical latent structure learning through online inference. HOLMES combines a variation on the nested Chinese Restaurant Process prior with sequential Monte Carlo inference to perform tractable trial-by-trial inference over hierarchical latent representations without explicit supervision over the latent structure. In simulations, HOLMES matched the predictive performance of flat models while learning more compact representations that supported one-shot backward transfer to higher-level latent categories. In a forward transfer task, HOLMES additionally achieved above-chance outcome prediction for stimuli with never-before-seen feature combinations, by exploiting abstract shape-level representations learned across diverse training instances. These results provide a tractable computational framework for discovering hierarchical structure in sequential data.
Abstract:Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires representations that support both. Online latent-cause models support incremental inference but assume flat partitions, whereas hierarchical Bayesian models capture multilevel structure but typically require offline inference. We introduce the \textbf{Hierarchical Online Learning of Multiscale Experience Structure (HOLMES) model}, a computational framework for hierarchical latent structure learning through online inference. HOLMES combines a variation on the nested Chinese Restaurant Process prior with sequential Monte Carlo inference to perform tractable trial-by-trial inference over hierarchical latent representations without explicit supervision over the latent structure. In simulations, HOLMES matched the predictive performance of flat models while learning more compact representations that supported one-shot backward transfer to higher-level latent categories. In a forward transfer task, HOLMES additionally achieved above-chance outcome prediction for stimuli with never-before-seen feature combinations, by exploiting abstract shape-level representations learned across diverse training instances. These results provide a tractable computational framework for discovering hierarchical structure in sequential data.
Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
arXiv:2603.19139 [cs.LG]
(or arXiv:2603.19139v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2603.19139 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 · 258 cuvinte
Subiecte conexe
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · 15 iul. 2026
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
arXiv · 1 sept. 2026
Accelerating Hierarchical Sparse Predictive Coding with Hybrid Amortized Inference
arXiv · 28 iul. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026