On DeepSeekMoE: Statistical Benefits of Shared Experts and Normalized Sigmoid Gating

• URL: http://arxiv.org/abs/2505.10860v1
• Date: Fri, 16 May 2025 04:58:18 GMT
• Title: On DeepSeekMoE: Statistical Benefits of Shared Experts and Normalized Sigmoid Gating
• Authors: Huy Nguyen, Thong T. Doan, Quang Pham, Nghi D. Q. Bui, Nhat Ho, Alessandro Rinaldo,
• Abstract summary: DeepSeekMoE stands out because of two unique features: the deployment of a shared expert strategy and of the normalized sigmoid gating mechanism.<n>We perform a convergence analysis of the expert estimation task to highlight the gains in sample efficiency for both the shared expert strategy and the normalized sigmoid gating.
• Score: 75.29576838162714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture of experts (MoE) methods are a key component in most large language model architectures, including the recent series of DeepSeek models. Compared to other MoE implementations, DeepSeekMoE stands out because of two unique features: the deployment of a shared expert strategy and of the normalized sigmoid gating mechanism. Despite the prominent role of DeepSeekMoE in the success of the DeepSeek series of models, there have been only a few attempts to justify theoretically the value of the shared expert strategy, while its normalized sigmoid gating has remained unexplored. To bridge this gap, we undertake a comprehensive theoretical study of these two features of DeepSeekMoE from a statistical perspective. We perform a convergence analysis of the expert estimation task to highlight the gains in sample efficiency for both the shared expert strategy and the normalized sigmoid gating, offering useful insights into the design of expert and gating structures. To verify empirically our theoretical findings, we carry out several experiments on both synthetic data and real-world datasets for (vision) language modeling tasks. Finally, we conduct an extensive empirical analysis of the router behaviors, ranging from router saturation, router change rate, to expert utilization.

Related papers

• Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations [48.890534958441016]
  We investigate domain specialization and expert redundancy in large-scale MoE models.<n>We propose a simple yet effective pruning framework, EASY-EP, to identify and retain only the most relevant experts.<n>Our method can achieve comparable performances and $2.99times$ throughput under the same memory budget with full DeepSeek-R1 with only half the experts.
  arXiv  Detail & Related papers  (2025-04-09T11:34:06Z)
• Convergence Rates for Softmax Gating Mixture of Experts [78.3687645289918]
  Mixture of experts (MoE) has emerged as an effective framework to advance the efficiency and scalability of machine learning models.<n>Central to the success of MoE is an adaptive softmax gating mechanism which takes responsibility for determining the relevance of each expert to a given input and then dynamically assigning experts their respective weights.<n>We perform a convergence analysis of parameter estimation and expert estimation under the MoE equipped with the standard softmax gating or its variants, including a dense-to-sparse gating and a hierarchical softmax gating.
  arXiv  Detail & Related papers  (2025-03-05T06:11:24Z)
• On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions [29.130355774088205]
  Hierarchical Mixture of Experts (HMoE) excels in handling complex inputs and improving performance on targeted tasks.<n>Our analysis highlights the advantages of using the Laplace gating function over the traditional Softmax gating within the HMoE frameworks.<n> Empirical validation across diverse scenarios supports these theoretical claims.
  arXiv  Detail & Related papers  (2024-10-03T19:28:52Z)
• Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study [65.11303133775857]
  Mixture-of-Experts (MoE) computation amalgamates predictions from several specialized sub-models (referred to as experts) Sparse MoE selectively engages only a limited number, or even just one expert, significantly reducing overhead while empirically preserving, and sometimes even enhancing, performance.
  arXiv  Detail & Related papers  (2024-03-26T05:48:02Z)
• On Least Square Estimation in Softmax Gating Mixture of Experts [78.3687645289918]
  We investigate the performance of the least squares estimators (LSE) under a deterministic MoE model. We establish a condition called strong identifiability to characterize the convergence behavior of various types of expert functions. Our findings have important practical implications for expert selection.
  arXiv  Detail & Related papers  (2024-02-05T12:31:18Z)
• DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models [26.447210565680116]
  We propose the DeepSeekMoE architecture towards ultimate expert specialization. It involves two principal strategies: (1) finely segmenting the experts into $mN$ ones and activating $mK$ from them, allowing for a more flexible combination of activated experts. We show that DeepSeekMoE achieves comparable performance with GShard 2.9B, which has 1.5 times the expert parameters and computation.
  arXiv  Detail & Related papers  (2024-01-11T17:31:42Z)
• Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy [84.11508381847929]
  Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks. We propose M-SMoE, which leverages routing statistics to guide expert merging. Our MC-SMoE achieves up to 80% memory and a 20% FLOPs reduction, with virtually no loss in performance.
  arXiv  Detail & Related papers  (2023-10-02T16:51:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.