# Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces

arXiv: https://arxiv.org/abs/2605.02950 · HTML: https://mlsanity.com/paper/2605.02950/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling](https://mlsanity.com/paper/2104.06967/) (2021)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [A Reasoning-Focused Legal Retrieval Benchmark](https://mlsanity.com/paper/2505.03970/) (2025)
- [Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation](https://mlsanity.com/paper/2406.19760/) (2024)
- [Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs](https://mlsanity.com/paper/2410.06581/) (2024)
- [Adam: Dense Retrieval Distillation with Adaptive Dark Examples](https://mlsanity.com/paper/2212.10192/) (2022)
- [On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach](https://mlsanity.com/paper/2304.01300/) (2023)
- [Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent](https://mlsanity.com/paper/2407.04335/) (2024)
- [Operator-Theoretic Framework for Gradient-Free Federated Learning](https://mlsanity.com/paper/2512.01025/) (2025)

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

- [Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions](https://mlsanity.com/paper/2609.32652/) (2026)

## Abstract (arXiv)

Transformer-based semantic encoders are effective for retrieval, but in many deployments the recurring bottleneck is online query encoding rather than offline corpus indexing. This paper studies whether, once a strong teacher representation space and corpus index are fixed, repeated neural query encoding can be replaced by a substantially lighter and analytically explicit estimator. We formulate fixed-teacher lexical-to-semantic encoding as a conditional-mean estimation problem in which the target semantic vector is represented as a noisy mixture of semantic prototypes weighted by posterior cluster probabilities. Kernel Affine Hull Machine (KAHM) geometry is used to estimate these posterior weights from inexpensive lexical features in an explicitly identified RKHS hypothesis space, and the semantic prototypes are refined by normalized least-mean-squares updates from noisy teacher embeddings. This yields a backpropagation-free query-side encoder together with an end-to-end error decomposition into posterior-approximation, finite-sample/generalization, and teacher-noise terms. We instantiate the approach on a controlled Austrian-law retrieval benchmark with 5,000 test queries, 84 candidate laws, and 10,762 aligned retrieval units, using law-specific encoders into a frozen Mixedbread embedding space. Among evaluation-matched learned adapters, KAHM achieves the strongest teacher-space reconstruction and the best rank-sensitive retrieval performance at all evaluated cutoffs. At k=20, it obtains MRR@20 = 0.504, Hit@20 = 0.694, and Top-1 Accuracy = 0.411, while reducing online per-query time by 8.53 relative to direct transformer query encoding in the reported CPU setting. The results support KAHMs as compute-efficient encoders for supervised fixed-representation deployment regimes.