Metraipolis › archive › dc_fd50fea23b39
Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training — arXiv:2608.11061
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11061
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:19:33.950Z
- SHA-256 of the archived text
c284dbd7b3448a8607523af3e8338d09703fb63d4529b427a42846115d004391- Stable URL of this page
https://metraipolis.com/documento/dc_fd50fea23b39
How to cite
Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training — arXiv:2608.11061 — arXiv (en), https://arxiv.org/abs/2608.11061 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd50fea23b39 (Metraipolis archive dc_fd50fea23b39, sha256 c284dbd7b3448a8607523af3e8338d09703fb63d4529b427a42846115d004391)
BibTeX
@misc{dcfd50fea23b39,
title = {Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training — arXiv:2608.11061},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11061},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd50fea23b39; sha256 c284dbd7b3448a8607523af3e8338d09703fb63d4529b427a42846115d004391},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11061. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible items $K$, the final classification layer dominates memory, requiring $O(nK)$ logits and gradients to materialize for a batch of $n$ examples. Sampled softmax reduces this cost by restricting the objective to only $k \ll K$ candidate negative items, resulting in an $O(nk)$ memory. However, for a fixed budget $B = n k$, it remains unclear whether one should prioritize larger batches or the inclusion of more negative items. We address this question by analyzing sampled-softmax training under a fixed memory constraint. Under standard smoothness and variance assumptions, our theoretical evidence suggests that the fastest convergence arises from an $ n \sim B, k \sim 1$ allocation. So, an actionable rule is to include as many objects as possible given computational constraints. Our theory is supported by controlled synthetic and synthetic and four real sequential recommendation benchmarks, including MovieLens-20M. The suggested configuration achieve faster convergence and better final recommendation quality than imbalanced alternatives within the same memory constraint. These findings provide a theoretical and empirical foundation for configuring memory during the training of recommender systems. Code, reproducibility materials, and all scripts for generating figures are available at this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.11061 — 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 2026-10-19T06:11:45.108Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).