Generalization and Scaling Laws for Mixture-of-Experts Transformers
We develop a theory of generalization and scaling for Mixture-of-Experts (MoE) Transformers that cleanly separates \emph{active} per-input capacity from routing combinatorics. By conditioning on fixed routing patterns and union-bounding across them, we derive a sup-norm covering-number bound whose metric entropy scales with the active parameter budget and incurs a MoE-specific routing overhead. Combined with a standard ERM analysis for squared loss, this yields a generalization bound under a $d$-dimensional manifold data model and $C^β$ targets, showing that approximation and estimation trade off as in dense networks once active parameters are accounted for appropriately. We further prove a constructive approximation theorem for MoE architectures, showing that, under the approximation construction, error can decrease either by scaling active capacity or by increasing the number of experts, depending on the dominant bottleneck. From these results we derive neural scaling laws for model size, data size, and compute-optimal tradeoffs. Overall, our results provide a transparent statistical reference point for reasoning about MoE scaling, clarifying which behaviors are certified by worst-case theory and which must arise from data-dependent routing structure or optimization dynamics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Scaling Laws for Fine-Grained Mixture of Experts
Mixture of Experts (MoE) models have emerged as a primary solution for reducing the computational cost of Large Language Models. In this work, we analyze their scaling properties, incorporating an expanded range of varia…
Mixture-of-ExpertsScaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment. Our work investigates the transferability and discrepancies of scaling laws b…
Mixture-of-ExpertsJoint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
Mixture of Experts (MoE) architectures have significantly increased computational efficiency in both research and real-world applications of large-scale machine learning models. However, their scalability and efficiency …
Computational EfficiencyMixture-of-ExpertsMixtures of Experts Unlock Parameter Scaling for Deep RL
The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for rein…
reinforcement-learningReinforcement LearningSelf-Supervised LearningOptimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
This paper presents a novel extension of neural scaling laws to Mixture-of-Experts (MoE) models, focusing on the optimal allocation of compute between expert and attention sub-layers. As MoE architectures have emerged as…