Factorization Regret mediates compositional generalization in latent space
cs.LG
Submitted: 2026-03-28
Updated: 2026-09-27
License: http://creativecommons.org/publicdomain/zero/1.0/
The gist: Are there still barriers to generalization once all relevant variables are known? We consider the challenge of generalizing to a novel combination of task-relevant latent variables in the Cognitive
Terminology
Abstract
Are there still barriers to generalization once all relevant variables are known? We consider the challenge of generalizing to a novel combination of task-relevant latent variables in the Cognitive Gridworld, a stationary Partially Observable Markov Decision Process where observations are generated by latent variables with parametric interactions. We establish Factorization Regret as an information-theoretic quantity measuring the contribution of latent variable interactions to task performance. Using this metric, we explain the sub-optimality of Echo State Networks and uncover a failure mode whereby confidence becomes decoupled from accuracy. This suggests that utilizing interactions between relevant variables is a non-trivial capability. We next introduce Representation Classification Chains to show that latent variable interactions and how to infer the variables' values can be learned together through Reinforcement Learning. Solving this variational inference problem enables generalization to novel combinations of relevant variables. Lastly, we demonstrate that once interactions are learned, imagined experience is sufficient for zero-shot control. In summary, we develop and motivate a minimal, theoretically grounded setting for research into generalization from experience.
Sources
- Is Conditional Generative Modeling all you need for Decision-Making?
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- On the Measure of Intelligence
- ARC Prize 2024: Technical Report
- Active Learning with Partial Feedback
- Meta-learning of Sequential Strategies
- A Generalist Agent
- Finding Approximate POMDP solutions Through Belief Compression
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks