Kernel Affine Hull Machines for Compute-Efficient Query-Side Semantic Encoding

• URL: http://arxiv.org/abs/2605.02950v1
• Date: Fri, 01 May 2026 17:46:26 GMT
• Title: Kernel Affine Hull Machines for Compute-Efficient Query-Side Semantic Encoding
• Abstract summary: Transformer-based semantic retrieval is highly effective, yet in many deployments the dominant cost lies in online query encoding rather than corpus indexing.<n>We study the fixed-teacher query-adaptation problem and ask whether repeated neural inference can be replaced by a lightweight, analytically explicit estimator without degrading decision-relevant retrieval quality.<n>We propose Kernel Affine Hull Machines (KAHMs), which map inexpensive lexical features into a frozen semantic embedding space by estimating prototype-mixture weights in a rigorously specified RKHS.<n>On a controlled Austrian-law benchmark (5,000 queries; 84 laws; 10,762 units), KAHM attains the strongest
• Score: 1.4021008554367664
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based semantic retrieval is highly effective, yet in many deployments the dominant cost lies in online query encoding rather than corpus indexing. We study the fixed-teacher query-adaptation problem and ask whether repeated neural inference can be replaced by a lightweight, analytically explicit estimator without degrading decision-relevant retrieval quality. We propose Kernel Affine Hull Machines (KAHMs), which map inexpensive lexical features into a frozen semantic embedding space by estimating prototype-mixture weights in a rigorously specified RKHS and refining prototypes via normalized least-mean-squares, yielding a transparent decomposition of encoding error into posterior-approximation, generalization, and teacher-noise components. On a controlled Austrian-law benchmark (5,000 queries; 84 laws; 10,762 units), KAHM attains the strongest teacher-space reconstruction among matched learned adapters (MSE 0.000091, R^2 0.9071, cosine 0.9536) and consistently leads rank-sensitive metrics, including mean reciprocal rank at 20 (MRR@20, the average inverse rank of the first relevant result within the top 20), Hit rate at 20 (Hit@20, the fraction of queries with at least one relevant result in the top 20), and Top-1 accuracy (the fraction of queries whose correct item is ranked first), with scores of 0.504, 0.694, and 0.411, respectively. It also reduces per-query latency by a factor of 8.5 relative to direct transformer encoding. These results demonstrate that, in fixed-teacher regimes, lightweight geometric estimators can substitute for online neural encoding, preserving retrieval performance while substantially improving efficiency and interpretability.

Related papers

• SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG [0.0]
  We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.<n>We evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers)<n>Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K.
  arXiv  Detail & Related papers  (2026-08-04T16:04:07Z)
• TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings [2.4483752182160954]
  We evaluate TabPFN as a plug-and-play, zero-gradient classification head for frozen image, text, and audio encoders.<n>Across 22,820 evaluation episodes spanning 14 datasets, 11 encoders, and three modalities, TabPFN achieves the best mean rank among nine classification heads on both negative log-likelihood (NLL) and expected calibration error (ECE)<n>Its accuracy advantage is conditional, concentrating at moderate-to-high shot counts and low-to-moderate feature dimensions.
  arXiv  Detail & Related papers  (2026-07-13T02:11:27Z)
• ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion [0.0]
  We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time.<n>On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K.<n>Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.
  arXiv  Detail & Related papers  (2026-06-12T08:51:24Z)
• Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data? [82.09573568241724]
  EssenceBench is a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA)<n>Our approach yields superior compression results with lower reconstruction error and markedly higher efficiency.<n>On the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.
  arXiv  Detail & Related papers  (2025-10-12T05:38:10Z)
• Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition [77.4863142882136]
  Cross-encoder models are prohibitively expensive for direct k-nearest neighbor (k-NN) search. We propose ADACUR, a method that adaptively, iteratively, and efficiently minimizes the approximation error for the practically important top-k neighbors.
  arXiv  Detail & Related papers  (2023-05-04T17:01:17Z)
• Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining [61.09807522366773]
  We introduce an algorithm that approximates the softmax with provable bounds and that dynamically maintains the tree. In our study on datasets with over twenty million targets, our approach cuts error by half in relation to oracle brute-force negative mining.
  arXiv  Detail & Related papers  (2023-03-27T15:18:32Z)
• Rapid Person Re-Identification via Sub-space Consistency Regularization [51.76876061721556]
  Person Re-Identification (ReID) matches pedestrians across disjoint cameras. Existing ReID methods adopting real-value feature descriptors have achieved high accuracy, but they are low in efficiency due to the slow Euclidean distance computation. We propose a novel Sub-space Consistency Regularization (SCR) algorithm that can speed up the ReID procedure by 0.25$ times.
  arXiv  Detail & Related papers  (2022-07-13T02:44:05Z)
• Accelerating Attention through Gradient-Based Learned Runtime Pruning [9.109136535767478]
  Self-attention is a key enabler of state-of-art accuracy for transformer-based Natural Language Processing models. This paper formulates its search through a soft differentiable regularizer integrated into the loss function of the training. We devise a bit-serial architecture, dubbed LeOPArd, for transformer language models with bit-level early termination microarchitectural mechanism.
  arXiv  Detail & Related papers  (2022-04-07T05:31:13Z)
• Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection [0.0]
  Reconstruction autoencoder-based methods deal with the problem by using input reconstruction error as a metric of novelty vs. normality. We introduce semantic reconstruction, data certainty decomposition and normalized L2 distance to substantially improve original methods. Our method works without any additional data, hard-to-implement structure, time-consuming pipeline, and even harming the classification accuracy of known classes.
  arXiv  Detail & Related papers  (2022-03-04T09:04:55Z)
• Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding [57.08875260900373]
  We propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC) SAD aggressively decodes as many tokens as possible in parallel instead of always decoding only one token in each step to improve computational parallelism. Experiments in both English and Chinese GEC benchmarks show that aggressive decoding could yield the same predictions but with a significant speedup for online inference.
  arXiv  Detail & Related papers  (2021-06-09T10:30:59Z)
• A Scalable, Adaptive and Sound Nonconvex Regularizer for Low-rank Matrix Completion [60.52730146391456]
  We propose a new non scalable low-rank regularizer called "nuclear Frobenius norm" regularizer, which is adaptive and sound. It bypasses the computation of singular values and allows fast optimization by algorithms. It obtains state-of-the-art recovery performance while being the fastest in existing matrix learning methods.
  arXiv  Detail & Related papers  (2020-08-14T18:47:58Z)
• ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning [91.13797346047984]
  We introduce ADAHESSIAN, a second order optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates. We show that ADAHESSIAN achieves new state-of-the-art results by a large margin as compared to other adaptive optimization methods.
  arXiv  Detail & Related papers  (2020-06-01T05:00:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.