arXiv AI
Dissociating performance from compositional feature learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 22
Disassociating performance from compositional feature learning
arXiv:2505.09716v4 Announce Type: replace Abstract: Out-of-distribution (OOD) generalisation through composition requires a system to discover invariant properties from input-output associations and...
Hugging Face Trending Papers
Jun 22
Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions
Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?
arXiv AI
Sep 10
A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition
The paper presents a necessary and sufficient condition for provable compositional generalization in neural networks, identifying two key principles: structural alignment and unambiguous minimized representations. It rigorously proves this condition, verifies it in Lean 4, and demonstrates its applicability in few-shot settings, including the SCAN jump task. The authors also outline an algorithmic approach and illustrate it with a minimal example, all derived purely from mathematical analysis without empirical validation.
arXiv Machine Learning
Jul 7
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
arXiv:2602. 24264v2 Announce Type: replace-cross Abstract: Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems.
arXiv Computer Vision
Oct 22
Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models
arXiv:2610.29811v1 Announce Type: new Abstract: Compositional zero-shot learning (CZSL) aims to recognize novel combinations of previously observed objects and attributes. Prior work showed that larg...
arXiv AI
Jun 9
Muon Learns More Robust and Transferable Features than Adam
arXiv:2606. 09658v1 Announce Type: cross Abstract: Muon has recently emerged as a state-of-the-art optimizer for pretraining Large Language Models (LLMs) and vision classifiers.