arXiv:2511. 08307v2 Announce Type: replace-cross Abstract: Generative models, such as large language models or text-to-image diffusion models, can generate relevant responses to user-given queries.
arXiv:2607. 23480v1 Announce Type: new Abstract: Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable.
arXiv:2605. 17779v2 Announce Type: replace Abstract: Generative recommendation reformulates recommendation as next-token prediction over discrete semantic identifiers (IDs).
arXiv:2508. 20330v5 Announce Type: replace Abstract: Combinatorial optimization problems are ubiquitous in science and engineering.
arXiv:2511. 02496v2 Announce Type: replace Abstract: We study latent geometry as an explicit component of representation quality in data-scarce learning.
The paper investigates nonlinear dimensionality reduction for Bayesian optimisation (BO) by transforming high‑dimensional black‑box optimisation problems into a sequence of low‑dimensional latent‑space BO (LSBO) tasks. It extends earlier linear embedding approaches by using variational autoencoders (VAEs), deep metric loss, and adaptive retraining to better capture nonlinear structure, and couples LSBO with sequential domain reduction (SDR‑LSBO) to progressively narrow search domains. Experiments on GPU‑accelerated BoTorch with Matérn‑5/2 Gaussian‑process surrogates show that VAE‑based LSBO outperforms adaptive linear embeddings, and the authors provide a theoretical analysis of latent‑space error versus representation gap under PAC‑Bayes conditions.
SABLE is a Bayesian optimisation method designed for high‑dimensional latent spaces where the latent dimension far exceeds the evaluation budget. It uses a Bayesian affine surrogate that decomposes each query into an in‑span component optimized by expected improvement and an off‑span component governed by a scalar norm, with a finite‑horizon schedule to avoid under‑exploration. A recompression scheme reduces the number of pseudo‑observations to ≠O(M), keeping refitting costs manageable while achieving high sample efficiency and rapid decision times on synthetic and latent‑space optimisation tasks.
arXiv:2610.19351v1 Announce Type: cross Abstract: In many modern applications, obtaining response variables is costly, time-consuming, or technically challenging, making it impractical to measure out...
arXiv:2606. 02765v1 Announce Type: cross Abstract: Model dimension ($d_{model}$) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature representation remains under-explored.
arXiv:2601. 20844v3 Announce Type: replace-cross Abstract: This paper studies the Minimal Embeddable Dimension (MED): the least dimension in which there exists a configuration of $m$ object vectors so that every subset of size at most $k$ is exactly retrieved by score comparison.
arXiv:2608. 15121v1 Announce Type: cross Abstract: Sufficient dimension reduction (SDR) seeks the minimal subspace of the predictors that captures the full conditional distribution of the response, which is known as the central subspace (CS).
arXiv:2610.07045v1 Announce Type: cross Abstract: Many scientific studies allow costly auxiliary information to be collected during data labeling but not at deployment. Examples include diagnostic te...