REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency

• URL: http://arxiv.org/abs/2602.04677v1
• Date: Wed, 04 Feb 2026 15:50:53 GMT
• Title: REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency
• Authors: Ondrej Tybl, Lukas Neumann,
• Abstract summary: We introduce REDistill, a principled framework grounded in robust statistics.<n>Redistill replaces the standard KD objective with a power divergence loss, a generalization of KL divergence.<n>Experiments on CIFAR-100 and ImageNet-1k demonstrate that REDistill consistently improves student accuracy in diverse teacher-student architectures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations - typically based on Kullback-Leibler divergence - assume that the teacher provides reliable soft targets. In practice, teacher predictions are often noisy or overconfident, and existing correction-based approaches rely on ad-hoc heuristics and extensive hyper-parameter tuning, which hinders generalization. We introduce REDistill (Robust Estimator Distillation), a simple yet principled framework grounded in robust statistics. REDistill replaces the standard KD objective with a power divergence loss, a generalization of KL divergence that adaptively downweights unreliable teacher output while preserving informative logit relationships. This formulation provides a unified and interpretable treatment of teacher noise, requires only logits, integrates seamlessly into existing KD pipelines, and incurs negligible computational overhead. Extensive experiments on CIFAR-100 and ImageNet-1k demonstrate that REDistill consistently improves student accuracy in diverse teacher-student architectures. Remarkably, it achieves these gains without model-specific hyper-parameter tuning, underscoring its robustness and strong generalization to unseen teacher-student pairs.

Related papers

• Reinforcement-aware Knowledge Distillation for LLM Reasoning [63.53679456364683]
  Reinforcement learning (RL) post-training has recently driven gains in long chain-of-thought reasoning large language models (LLMs)<n>Most existing knowledge distillation methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization.<n>We propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update.
  arXiv  Detail & Related papers  (2026-02-26T00:20:39Z)
• Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation [50.19746127327559]
  We propose a new tail-aware divergence that decouples the contribution of the teacher model's top-K predicted probabilities from that of lower-probability predictions.<n> Experimental results demonstrate that our modified distillation method yields competitive performance in both pre-training and supervised distillation of decoder models.
  arXiv  Detail & Related papers  (2026-02-24T11:54:06Z)
• SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines [82.00660447875266]
  Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs.<n>We rigorously analyze the convergence behavior of students trained with Gradient Descent (SGD)<n>Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision.<n>Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD.
  arXiv  Detail & Related papers  (2026-01-04T11:09:49Z)
• Biased Teacher, Balanced Student [0.0]
  Long-Tailed Knowledge Distillation (LTKD) is a novel framework tailored for class-imbalanced scenarios.<n>Experiments on CIFAR-100-LT, TinyImageNet-LT, and ImageNet-LT show that LTKD consistently outperforms existing KD methods.
  arXiv  Detail & Related papers  (2025-06-23T10:46:44Z)
• ToDi: Token-wise Distillation via Fine-Grained Divergence Control [9.958797874295355]
  Token-wise Distillation (ToDi) is a novel method that adaptively combines Forward KL and Reverse KL per token using a sigmoid-based weighting function.<n>ToDi consistently outperforms recent distillation baselines using uniform or less granular strategies.
  arXiv  Detail & Related papers  (2025-05-22T06:51:16Z)
• Cross-View Consistency Regularisation for Knowledge Distillation [13.918476599394603]
  This work is inspired by the success of cross-view learning in fields such as semi-supervised learning.<n>We introduce within-view and cross-view regularisations to standard logit-based distillation frameworks.<n>We also perform confidence-based soft label mining to improve the quality of distilling signals from the teacher.
  arXiv  Detail & Related papers  (2024-12-21T05:41:47Z)
• Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching [0.09999629695552192]
  Correlation Matching Knowledge Distillation (CMKD) method combines the Pearson and Spearman correlation coefficients-based KD loss to achieve more efficient and robust distillation from a stronger teacher model. CMKD is simple yet practical, and extensive experiments demonstrate that it can consistently achieve state-of-the-art performance on CIRAR-100 and ImageNet.
  arXiv  Detail & Related papers  (2024-10-09T05:42:47Z)
• Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge [17.382306203152943]
  Dynamic Guidance Adversarial Distillation (DGAD) framework tackles the challenge of differential sample importance. DGAD employs Misclassification-Aware Partitioning (MAP) to dynamically tailor the distillation focus. Error-corrective Label Swapping (ELS) corrects misclassifications of the teacher on both clean and adversarially perturbed inputs.
  arXiv  Detail & Related papers  (2024-09-03T05:52:37Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Knowledge Distillation Performs Partial Variance Reduction [93.6365393721122]
  Knowledge distillation is a popular approach for enhancing the performance of ''student'' models. The underlying mechanics behind knowledge distillation (KD) are still not fully understood. We show that KD can be interpreted as a novel type of variance reduction mechanism.
  arXiv  Detail & Related papers  (2023-05-27T21:25:55Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)

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.