# From HNSW to Information-Theoretic Binarization: Rethinking the Architecture of Scalable Vector Search

arXiv: https://arxiv.org/abs/2601.11557 · HTML: https://mlsanity.com/paper/2601.11557/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Vector search and ANN indexes, one of 15 directions in Retrieval-augmented generation.
- Builds on 8 of its 53 references that are in the map.
- First posted on arXiv 16 Dec 2025.

## Placed in

- Retrieval-augmented generation / [Vector search and ANN indexes](https://mlsanity.com/rag/vector-search-and-ann-indexes/)

## Builds on (most cited first, 8 of 8)

- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge](https://mlsanity.com/paper/2310.11703/) (2023)
- [MAIR: A Massive Benchmark for Evaluating Instructed Retrieval](https://mlsanity.com/paper/2410.10127/) (2024)
- [Experimental Analysis of Locality Sensitive Hashing Techniques for High-Dimensional Approximate Nearest Neighbor Searches](https://mlsanity.com/paper/2006.11285/) (2020)
- [Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2410.20381/) (2024)
- [Efficient Vector Search on Disaggregated Memory with d-HNSW](https://mlsanity.com/paper/2505.11783/) (2025)

## Built on by (most cited first, 1 of 1)

- [Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents](https://mlsanity.com/paper/2604.22085/) (2026)

## Abstract (arXiv)

Modern semantic search and retrieval-augmented generation (RAG) systems rely predominantly on in-memory approximate nearest neighbor (ANN) indexes over high-precision floating-point vectors, resulting in escalating operational cost and inherent trade-offs between latency, throughput, and retrieval accuracy. This paper analyzes the architectural limitations of the dominant "HNSW + float32 + cosine similarity" stack and evaluates existing cost-reduction strategies, including storage disaggregation and lossy vector quantization, which inevitably sacrifice either performance or accuracy. We introduce and empirically evaluate an alternative information-theoretic architecture based on maximally informative binarization (MIB), efficient bitwise distance metrics, and an information-theoretic scoring (ITS) mechanism. Unlike conventional ANN systems, this approach enables exhaustive search over compact binary representations, allowing deterministic retrieval and eliminating accuracy degradation under high query concurrency. Using the MAIR benchmark across 14 datasets and 10,038 queries, we compare this architecture against Elasticsearch, Pinecone, PGVector, and Qdrant. Results demonstrate retrieval quality comparable to full-precision systems, while achieving substantially lower latency and maintaining constant throughput at high request rates. We show that this architectural shift enables a truly serverless, cost-per-query deployment model, challenging the necessity of large in-memory ANN indexes for high-quality semantic search.