analiza aiqbench
GeoRVQ introduces a novel training objective that aligns residual vector quantization directly with the local response of frozen waveform decoders, offering a more efficient path to preserving critical physiological events like R-peaks. By prioritizing decoder-induced costs over standard Euclidean distances, this approach significantly reduces decoded distance and improves event detection metrics without demanding massive increases in exact token accuracy. This work advances the field of medical signal processing by demonstrating that geometry-aware modeling yields superior reconstruction quality for vital sign waveforms.
GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals
arXiv:2609.27018v1 Announce Type: new Abstract: Residual vector quantization (RVQ) turns physiological waveforms into compact token sequences, but conventional masked modeling treats every incorrect token as equally costly. We propose GeoRVQ, a coarse-to-fine masked token model whose objective reflects the local response of a frozen waveform decoder. Decoder-induced costs define geometry-aware soft targets and expected distortion, while quantizer-causal prediction follows residual dependencies from coarse to fine levels. In a descriptive aggregate over MIMIC-IV Waveform, VitalDB, and CODE-15\%, GeoRVQ increases exact token accuracy from $.133\pm.004$ to $.143\pm.003$, reduces decoded distance from $.606\pm.006$ to $.393\pm.007$, and increases R-peak F1 from $.784\pm.004$ to $.837\pm.008$ under matched model and training conditions. Across 45 held-out code substitutions, decoder-induced cost has a Spearman correlation of $.85$ with realized decoded cost, compared with $.54$ for Euclidean codeword distance. These results indicate that decoder-aware objectives can improve waveform and event preservation without requiring a large increase in exact token accuracy.
Abstract:Residual vector quantization (RVQ) turns physiological waveforms into compact token sequences, but conventional masked modeling treats every incorrect token as equally costly. We propose GeoRVQ, a coarse-to-fine masked token model whose objective reflects the local response of a frozen waveform decoder. Decoder-induced costs define geometry-aware soft targets and expected distortion, while quantizer-causal prediction follows residual dependencies from coarse to fine levels. In a descriptive aggregate over MIMIC-IV Waveform, VitalDB, and CODE-15\%, GeoRVQ increases exact token accuracy from $.133\pm.004$ to $.143\pm.003$, reduces decoded distance from $.606\pm.006$ to $.393\pm.007$, and increases R-peak F1 from $.784\pm.004$ to $.837\pm.008$ under matched model and training conditions. Across 45 held-out code substitutions, decoder-induced cost has a Spearman correlation of $.85$ with realized decoded cost, compared with $.54$ for Euclidean codeword distance. These results indicate that decoder-aware objectives can improve waveform and event preservation without requiring a large increase in exact token accuracy.
Machine Learning (cs.LG)
arXiv:2609.27018 [cs.LG]
(or arXiv:2609.27018v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.27018 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 240 cuvinte
Subiecte conexe
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026
Predictive Geometry of Hidden Trajectories in Transformers
arXiv · 1 oct. 2026
GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models
arXiv · 6 oct. 2026
Geometry-Aware Hyperbolic Residual Quantization
arXiv · 24 sept. 2026