Saved in:
Bibliographic Details
Main Authors: Jin, Linghao, Shi, Chufan, Wang, Huijuan, Wen, Nuan, Liu, Zhengzhong, Xing, Eric, Ma, Xuezhe
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916011565907968
author Jin, Linghao
Shi, Chufan
Wang, Huijuan
Wen, Nuan
Liu, Zhengzhong
Xing, Eric
Ma, Xuezhe
author_facet Jin, Linghao
Shi, Chufan
Wang, Huijuan
Wen, Nuan
Liu, Zhengzhong
Xing, Eric
Ma, Xuezhe
contents Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active experts rather than the total pool of E experts. Yet, this asymmetry creates an MoE efficiency paradox in practice: adding more experts balloons memory and communication costs, making actual training inefficient. We argue that this bottleneck arises in part because current MoE training allocates too many experts from the beginning, even though early-stage data may not fully utilize such capacity. Motivated by this, we propose EMO, a simple progressive training framework that treats MoE capacity as expandable memory and grows the expert pool over the course of training. EMO explicitly models sparsity in scaling law to derive stage-wise compute-optimal token budgets for progressive expansion. Empirical results show that EMO matches the performance of a fixed-expert setup in large-scale experiments while improving wall-clock efficiency. It offers a surprisingly simple yet effective path to scalable MoE training, preserving the benefits of large expert pools while reducing both training time and GPU cost.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13247
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EMO: Frustratingly Easy Progressive Training of Extendable MoE
Jin, Linghao
Shi, Chufan
Wang, Huijuan
Wen, Nuan
Liu, Zhengzhong
Xing, Eric
Ma, Xuezhe
Machine Learning
Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active experts rather than the total pool of E experts. Yet, this asymmetry creates an MoE efficiency paradox in practice: adding more experts balloons memory and communication costs, making actual training inefficient. We argue that this bottleneck arises in part because current MoE training allocates too many experts from the beginning, even though early-stage data may not fully utilize such capacity. Motivated by this, we propose EMO, a simple progressive training framework that treats MoE capacity as expandable memory and grows the expert pool over the course of training. EMO explicitly models sparsity in scaling law to derive stage-wise compute-optimal token budgets for progressive expansion. Empirical results show that EMO matches the performance of a fixed-expert setup in large-scale experiments while improving wall-clock efficiency. It offers a surprisingly simple yet effective path to scalable MoE training, preserving the benefits of large expert pools while reducing both training time and GPU cost.
title EMO: Frustratingly Easy Progressive Training of Extendable MoE
topic Machine Learning
url https://arxiv.org/abs/2605.13247