Nonlocality distillation can outperform entanglement distillation

• URL: http://arxiv.org/abs/2603.00940v1
• Date: Sun, 01 Mar 2026 06:18:30 GMT
• Title: Nonlocality distillation can outperform entanglement distillation
• Authors: Peter Høyer, Jibran Rashid, Razeen ud Din,
• Abstract summary: In the limit of the number of copies of the shared state, entanglement distillation is guaranteed to work by generating a Bell state.<n>For a small number of copies of the state, we show that nonlocality distillation can achieve a higher CHSH value, even though optimal entanglement distillation requires communication.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Given the goal of maximizing CHSH violation, we compare the optimal strategies of entanglement and nonlocality distillation. In the limit of the number of copies of the shared state, entanglement distillation is guaranteed to work by generating a Bell state. For a small number of copies of the state, we show that nonlocality distillation can achieve a higher CHSH value, even though optimal entanglement distillation requires communication. Nonlocality distillation not only outperforms entanglement distillation but also demonstrates superior resource efficiency across multiple metrics for quantum resource estimation.

Related papers

• Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective [52.25797439810419]
  Existing defenses focus exclusively on text-based distillation, leaving the important logit-based distillation largely unexplored.<n>We characterize distillation-relevant information in teacher outputs using the conditional mutual information (CMI) between teacher logits and input queries conditioned on ground-truth labels.<n>We derive a CMI-inspired anti-distillation objective to optimize this transformation, which effectively removes distillation-relevant information while preserving output utility.
  arXiv  Detail & Related papers  (2026-02-03T11:16:59Z)
• Exponential Analysis for Entanglement Distillation [9.125120975190711]
  We study the reliability function of entanglement distillation, which specifies the optimal exponent of the decay of the distillation error.<n>We also extend the framework from the standard setting of known states to a black-box setting, where distillation is performed from a set of possible states.
  arXiv  Detail & Related papers  (2026-01-15T08:46:47Z)
• Antidistillation Sampling [97.86194163974783]
  Models that generate extended reasoning traces inadvertently produce rich token sequences that can facilitate model distillation.<n> Recognizing this vulnerability, model owners may seek sampling strategies that limit the effectiveness of distillation without compromising model performance.<n>Antidistillation sampling renders reasoning traces significantly less effective for distillation while preserving the model's practical utility.
  arXiv  Detail & Related papers  (2025-04-17T17:54:14Z)
• Enhancing Quantum Key Distribution with Entanglement Distillation and Classical Advantage Distillation [0.0]
  We present a two-stage distillation scheme concatenating entanglement distillation and classical advantage distillation.<n>We show that our scheme achieves finite key rates even in the high-noise regime.<n>The proposed scheme is well-suited for near-term quantum key distribution tasks.
  arXiv  Detail & Related papers  (2024-10-25T06:40:09Z)
• One-shot distillation with constant overhead using catalysts [3.771547570340179]
  Minimizing the overhead distillation is crucial for the realization of quantum computation and other technologies.<n>In particular, for magic state distillation our method paves a path for tackling the diverging batch size problem.<n>We extend techniques to dynamical quantum resources and show that mutual information determines one-shot catalytic channel transformation.
  arXiv  Detail & Related papers  (2024-10-18T15:41:52Z)
• Threshold (Q, P) Quantum Distillation [1.3412310262092788]
  We present a threshold quantum distillation task where the same objective is achieved but using fewer parties 'Q' Specifically, an arbitrary GHZ state can be distilled using just one party in the network, as both the success probability of the distillation protocol and the fidelity after the distillation are independent of the number of parties. For a general W-state, at least 'P-1' parties are required for the distillation, indicating a strong relationship between the distillation and the separability of such states.
  arXiv  Detail & Related papers  (2024-08-13T05:05:08Z)
• Leveraging Zero-Level Distillation to Generate High-Fidelity Magic States [0.8009842832476994]
  We evaluate the spatial temporal overhead of two-level distillation implementations generating relatively high-fidelity magic states. We refine the second-level 15-to-1 implementation in it to capitalize on the small footprint of zero-level distillation.
  arXiv  Detail & Related papers  (2024-04-15T12:42:29Z)
• Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation [96.92250565207017]
  We study the data efficiency and selection for the dataset distillation task. By re-formulating the dynamics of distillation, we provide insight into the inherent redundancy in the real dataset. We find the most contributing samples based on their causal effects on the distillation.
  arXiv  Detail & Related papers  (2023-05-28T06:53:41Z)
• KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling [52.11242317111469]
  We focus on the compression of DETR with knowledge distillation.<n>The main challenge in DETR distillation is the lack of consistent distillation points.<n>We propose the first general knowledge distillation paradigm for DETR with consistent distillation points sampling.
  arXiv  Detail & Related papers  (2022-11-15T11:52:30Z)
• Spot-adaptive Knowledge Distillation [39.23627955442595]
  We propose a new distillation strategy, termed spot-adaptive KD (SAKD) SAKD adaptively determines the distillation spots in the teacher network per sample, at every training iteration during the whole distillation period. Experiments with 10 state-of-the-art distillers are conducted to demonstrate the effectiveness of SAKD.
  arXiv  Detail & Related papers  (2022-05-05T02:21:32Z)
• Pre-trained Summarization Distillation [121.14806854092672]
  Recent work on distilling BERT for classification and regression tasks shows strong performance using direct knowledge distillation. Alternatively, machine translation practitioners distill using pseudo-labeling, where a small model is trained on the translations of a larger model. A third, simpler approach is to'shrink and fine-tune' (SFT), which avoids any explicit distillation by copying parameters to a smaller student model and then fine-tuning.
  arXiv  Detail & Related papers  (2020-10-24T23:15:43Z)
• Why distillation helps: a statistical perspective [69.90148901064747]
  Knowledge distillation is a technique for improving the performance of a simple "student" model. While this simple approach has proven widely effective, a basic question remains unresolved: why does distillation help? We show how distillation complements existing negative mining techniques for extreme multiclass retrieval.
  arXiv  Detail & Related papers  (2020-05-21T01:49:51Z)

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.