Metraipolis › archive › dc_4cc1ecfe4ff4

Superposed Latent Autoencoder — arXiv:2609.01158

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01158
License (as archived)
CC0-1.0
Archived
2026-10-17T06:33:57.844Z
SHA-256 of the archived text
a38a37181d7bbca908b64fe0eceba9ec5248d71f61f8152bdc7c45959541f8dd
Stable URL of this page
https://metraipolis.com/documento/dc_4cc1ecfe4ff4

How to cite

Superposed Latent Autoencoder — arXiv:2609.01158 — arXiv (en), https://arxiv.org/abs/2609.01158 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4cc1ecfe4ff4 (Metraipolis archive dc_4cc1ecfe4ff4, sha256 a38a37181d7bbca908b64fe0eceba9ec5248d71f61f8152bdc7c45959541f8dd)
BibTeX
@misc{dc4cc1ecfe4ff4,
  title = {Superposed Latent Autoencoder — arXiv:2609.01158},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01158},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4cc1ecfe4ff4; sha256 a38a37181d7bbca908b64fe0eceba9ec5248d71f61f8152bdc7c45959541f8dd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01158. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoencoders typically meet tight latent-memory budgets by making each latent representation smaller, sacrificing representational capacity. We ask a different question: can multiple wider latents be stored together instead? We introduce the Superposed Latent Autoencoder (SLAE), which preserves high-capacity latent representations while sharing storage through learned superposition. SLAE transforms latents into storage-friendly codes, binds them with randomized keys, superposes multiple codes into a single memory tensor, and learns to recover each latent before decoding. Under the same storage budget, SLAE replaces irreversible dimensional bottlenecks with structured interference that can be suppressed. Across CIFAR-10/100, SVHN, STL-10, Tiny ImageNet, and a wide range of memory budgets, SLAE substantially improves the reconstruction--memory tradeoff, reducing reconstruction error by up to 56% over conventional autoencoders at matched storage. Further analysis shows that SLAE's advantage comes from making wider representations usable under the same storage budget. These gains also extend beyond reconstruction: the information preserved by SLAE improves downstream classification by up to 16.79 percentage points under the same memory budget. Our results suggest a new principle for representation compression: instead of making every latent smaller, keep representations wide and let them share memory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01158 — 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 2026-10-17T06:15:12.865Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).