Intrinsic Task Symmetry Drives Generalization in Algorithmic Tasks
Grokking, the sudden transition from memorization to generalization, is characterized by the emergence of low-dimensional representations, yet the mechanism underlying this organization remains elusive. We propose that intrinsic task symmetries primarily drive grokking and shape the geometry of the model's representation space. We identify a consistent three-stage training dynamic underlying grokking: (i) memorization, (ii) symmetry acquisition, and (iii) geometric organization. We show that generalization emerges during the symmetry acquisition phase, after which representations reorganize into a structured, task-aligned geometry. We validate this symmetry-driven account across diverse algorithmic domains, including algebraic, structural, and relational reasoning tasks. Building on these findings, we introduce a symmetry-based diagnostic that anticipates the onset of generalization and propose strategies to accelerate it. Together, our results establish intrinsic symmetry as the key factor enabling neural networks to move beyond memorization and achieve robust algorithmic reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
Relational ReasoningSimilar Papers 제목 키워드 기반
Symmetries-enhanced Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample effi…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningScheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
Exploration in sparse reward reinforcement learning remains an open challenge. Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities …
Reinforcement LearningHIPO: Instruction Hierarchy via Constrained Reinforcement Learning
Hierarchical Instruction Following (HIF) refers to the problem of prompting large language models with a priority-ordered stack of instructions. Standard methods like RLHF and DPO typically fail in this problem since the…
Reinforcement LearningInstruction FollowingDreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statistical correlations rather than the environ…
Grokking From Abstraction to Intelligence
Grokking in modular arithmetic has established itself as the quintessential fruit fly experiment, serving as a critical domain for investigating the mechanistic origins of model generalization. Despite its significance, …