AI RESEARCH
IVF-TQ: Streaming-Robust Approximate Nearest Neighbor Search via a Codebook-Free Residual Layer
arXiv CS.LG
•
ArXi:2605.17415v1 Announce Type: new We propose IVF-TQ, an IVF index with a codebook-free residual layer: a fixed random rotation followed by precomputed Lloyd-Max scalar quantization depending only on (b, d). Only the IVF coarse partition is trained. Building on TurboQuant (Zandieh, 2025), the design substantially reduces a key failure mode of trained-codebook ANN indexes (PQ, OPQ, ScaNN): staleness under streaming ingestion. Empirical (3 seeds): Per-batch PQ re