Block-Sphere Vector Quantization

• URL: http://arxiv.org/abs/2605.19972v1
• Date: Tue, 19 May 2026 15:18:56 GMT
• Title: Block-Sphere Vector Quantization
• Abstract summary: Vector quantization is a fundamental primitive for scalable machine learning systems.<n>Recent rotation-based quantizers have introduced strong guarantees and empirical performance.<n>We introduce Block-Sphere Quantization (BlockQuant), a new rotation-based block quantization algorithm.
• Score: 35.41703011973504
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vector quantization is a fundamental primitive for scalable machine learning systems, enabling memory-efficient storage, fast retrieval, and compressed inference. Recent rotation-based quantizers such as EDEN, RabitQ, and TurboQuant have introduced strong guarantees and empirical performance, but the surrounding comparisons have been difficult to interpret because they rely on different distortion criteria, probability regimes, and implementation assumptions. As our first contribution, we provide a unified theoretical comparison of these methods and show that their relative advantages are criterion-dependent rather than absolute: EDEN and TurboQuant are favorable for MSE distortion, EDEN is also effective for expected inner-product distortion, and RabitQ provides strong high-probability control. This comparison further clarifies that EDEN provides particularly strong guarantees for expected distortion measures. As our second contribution, we introduce Block-Sphere Quantization (BlockQuant), a new rotation-based block quantization algorithm designed around the spherical geometry of randomly rotated vectors. Unlike coordinate-wise quantizers, BlockQuant quantizes blocks on the sphere, preserving the geometry of rotated embeddings more faithfully. We prove that this block-spherical design theoretically improves over the baselines considered in this paper for both reconstruction MSE and expected inner-product distortion. Our experiments on real embedding datasets and long-context LLM inference tasks show practical gains that are consistent with our theoretical improvements.

Related papers

• Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization [50.880384999888044]
  We develop misspecified GP bandit algorithms and derive regret bounds that characterize the trade-off between approximation error and information gain.<n>Our methods outperform full quantum kernels in sample efficiency, while substantially reducing computational overhead.
  arXiv  Detail & Related papers  (2026-07-01T15:38:00Z)
• Equivariant Evidential Deep Learning for Interatomic Potentials [55.6997213490859]
  Uncertainty quantification is critical for assessing the reliability of machine learning interatomic potentials in molecular dynamics simulations.<n>Existing UQ approaches for MLIPs are often limited by high computational cost or suboptimal performance.<n>We propose textitEquivariant Evidential Deep Learning for Interatomic Potentials ($texte2$IP), a backbone-agnostic framework that models atomic forces and their uncertainty jointly.
  arXiv  Detail & Related papers  (2026-02-11T02:00:25Z)
• Optimal Effective Hamiltonian for Quantum Computing and Simulation [1.0359978670015826]
  We establish the Least Action Unitary Transformation as the fundamental principle for effective models.<n>We validate this framework against experimental data from superconducting quantum processors.<n>This work provides a systematic, experimentally validated route for high-precision system learning and Hamiltonian engineering.
  arXiv  Detail & Related papers  (2026-02-03T15:09:29Z)
• Reinforcement Learning Using known Invariances [54.91261509214309]
  This paper develops a theoretical framework for incorporating known group symmetries into kernel-based reinforcement learning.<n>We show that symmetry-aware RL achieves significantly better performance than their standard kernel counterparts.
  arXiv  Detail & Related papers  (2025-11-05T13:56:14Z)
• On approximate quantum error correction for symmetric noise [8.099700053397278]
  We revisit the extendability-based semi-definite programming hierarchy introduced by Berta et al.<n>In particular, we combine noise symmetries - such as those present in multiple copies of the qubit depolarizing channel - with the permutational symmetry arising from the extendability of the optimization variable.<n>Our results contribute to narrowing the gap between theoretical developments in quantum information theory and their practical applications in the analysis of small-scale quantum error-correcting codes.
  arXiv  Detail & Related papers  (2025-07-16T15:20:07Z)
• TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate [13.14434628836727]
  Vector quantization aims to quantize high-dimensional Euclidean vectors while minimizing distortion in their geometric structure.<n>We propose TurboQuant to address both mean-squared error (MSE) and inner product distortion.<n>Our data-oblivious algorithms, suitable for online applications, achieve near-optimal distortion rates.
  arXiv  Detail & Related papers  (2025-04-28T15:05:35Z)
• A Unified Blockwise Measurement Design for Learning Quantum Channels and Lindbladians via Low-Rank Matrix Sensing [5.266892492931388]
  We propose a robust approach based on the matrix sensing techniques for quantum superoperator learning.<n>We provide theoretical guarantees for the identifiability and recovery of low-rank superoperators in the presence of noise.<n>Our approach employs alternating least squares (ALS) with acceleration for optimization in matrix sensing.
  arXiv  Detail & Related papers  (2025-01-23T20:36:45Z)
• Variance-Reducing Couplings for Random Features [57.73648780299374]
  Random features (RFs) are a popular technique to scale up kernel methods in machine learning. We find couplings to improve RFs defined on both Euclidean and discrete input spaces. We reach surprising conclusions about the benefits and limitations of variance reduction as a paradigm.
  arXiv  Detail & Related papers  (2024-05-26T12:25:09Z)
• Quantization of Large Language Models with an Overdetermined Basis [73.79368761182998]
  We introduce an algorithm for data quantization based on the principles of Kashin representation. Our findings demonstrate that Kashin Quantization achieves competitive or superior quality in model performance.
  arXiv  Detail & Related papers  (2024-04-15T12:38:46Z)
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN [51.02649432050852]
  PELICAN is a novel permutation equivariant and Lorentz invariant aggregator network. We present a study of the PELICAN algorithm architecture in the context of both tagging (classification) and reconstructing (regression) Lorentz-boosted top quarks. We extend the application of PELICAN to the tasks of identifying quark-initiated vs.gluon-initiated jets, and a multi-class identification across five separate target categories of jets.
  arXiv  Detail & Related papers  (2023-07-31T09:08:40Z)
• Convergence and Quantum Advantage of Trotterized MERA for Strongly-Correlated Systems [0.0]
  Trotterized MERA VQE is a promising route for the efficient investigation of strongly-correlated quantum many-body systems on quantum computers.<n>We show how the convergence can be substantially improved by building up the MERA layer by layer in the stage and by scanning through the phase diagram during optimization.
  arXiv  Detail & Related papers  (2023-03-15T20:09:45Z)
• Importance sampling for stochastic quantum simulations [68.8204255655161]
  We introduce the qDrift protocol, which builds random product formulas by sampling from the Hamiltonian according to the coefficients. We show that the simulation cost can be reduced while achieving the same accuracy, by considering the individual simulation cost during the sampling stage. Results are confirmed by numerical simulations performed on a lattice nuclear effective field theory.
  arXiv  Detail & Related papers  (2022-12-12T15:06:32Z)

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.