Metraipolis › archive › dc_29a015ddfb03
Distributionally Robust Mixture-of-Experts Training — arXiv:2610.07207
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07207
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:25.038Z
- SHA-256 of the archived text
d29c1bbb07d7126eb66fc284d62d6fd5dcfa9cba2bfb3f1934fc1fd97e6d3384- Stable URL of this page
https://metraipolis.com/documento/dc_29a015ddfb03
How to cite
Distributionally Robust Mixture-of-Experts Training — arXiv:2610.07207 — arXiv (en), https://arxiv.org/abs/2610.07207 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29a015ddfb03 (Metraipolis archive dc_29a015ddfb03, sha256 d29c1bbb07d7126eb66fc284d62d6fd5dcfa9cba2bfb3f1934fc1fd97e6d3384)
BibTeX
@misc{dc29a015ddfb03,
title = {Distributionally Robust Mixture-of-Experts Training — arXiv:2610.07207},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07207},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29a015ddfb03; sha256 d29c1bbb07d7126eb66fc284d62d6fd5dcfa9cba2bfb3f1934fc1fd97e6d3384},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07207. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creates a hidden reliability problem: when routing is imperfect, load-balanced models may send tokens to experts that are insufficiently trained for the assigned inputs. We propose Distributionally Robust MoE Training (DRMoET), a drop-in objective that treats layer-wise experts as endogenous robustness groups and optimizes high-loss routing outcomes rather than merely equalizing traffic. DRMoET updates a per-layer expert distribution by an entropy-regularized softmax rule on EMA-smoothed, activation-weighted expert losses, strengthening plausible non-top routing paths while preserving standard MoE computation. Under the FLAME-MoE recipe at 746M-total and 10.3B-total scales, DRMoET improves downstream averages over both standard FLAME-MoE and auxiliary-loss-free balancing. At 10.3B total parameters and 67B training tokens, DRMoET improves the seven-task average from 0.6625 to 0.6767, while the auxiliary-loss-free baseline achieves 0.6431. Mechanistic analyses show lower expert-loss variance with nearly unchanged mean loss, 4.3% lower excess loss under forced mid-$k$ misrouting, and improved domain-expert specialization. These results position routing robustness-not only utilization balance-as a practical objective for reliable sparse MoE scaling. Project page and code are available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.07207 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.687Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).