English
Related papers

Related papers: When Data Falls Short: Grokking Below the Critical…

200 papers

Neural collapse, i.e., the emergence of highly symmetric, class-wise clustered representations, is frequently observed in deep networks and is often assumed to reflect or enable generalization. In parallel, flatness of the loss landscape…

Machine Learning · Computer Science 2026-02-05 Ting Han , Linara Adilova , Henning Petzka , Jens Kleesiek , Michael Kamp

Neural networks trained by gradient descent (GD) have exhibited a number of surprising generalization behaviors. First, they can achieve a perfect fit to noisy training data and still generalize near-optimally, showing that overfitting can…

Machine Learning · Computer Science 2023-10-05 Zhiwei Xu , Yutong Wang , Spencer Frei , Gal Vardi , Wei Hu

Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…

Computation and Language · Computer Science 2019-12-10 Mitchell A. Gordon , Kevin Duh

Grokking, the abrupt transition from memorization to generalisation after extended training, suggests the presence of competing solution basins with distinct statistical properties. We study this phenomenon through the lens of Singular…

Machine Learning · Statistics 2026-05-08 Ben Cullen , Sergio Estan-Ruiz , Riya Danait , Jiayi Li

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…

Machine Learning · Computer Science 2019-12-24 Fabian Ruffy , Karanbir Chahal

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Machine Learning · Computer Science 2021-03-26 Zhenyan Hou , Wenxuan Fan

Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…

Machine Learning · Computer Science 2023-05-26 Shiya Luo , Defang Chen , Can Wang

Knowledge distillation deploys complex machine learning models in resource-constrained environments by training a smaller student model to emulate internal representations of a complex teacher model. However, the teacher's representations…

Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its…

Machine Learning · Computer Science 2025-12-11 Zhengquan Luo , Zhiqiang Xu

Cross-modal knowledge distillation deals with transferring knowledge from a model trained with superior modalities (Teacher) to another model trained with weak modalities (Student). Existing approaches require paired training examples exist…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Long Zhao , Xi Peng , Yuxiao Chen , Mubbasir Kapadia , Dimitris N. Metaxas

Knowledge distillation is a popular machine learning technique that aims to transfer knowledge from a large 'teacher' network to a smaller 'student' network and improve the student's performance by training it to emulate the teacher. In…

Machine Learning · Computer Science 2022-10-19 Sushil Thapa

Knowledge distillation (KD) has enabled remarkable progress in model compression and knowledge transfer. However, KD requires a large volume of original data or their representation statistics that are not usually available in practice.…

Machine Learning · Computer Science 2021-02-11 Pengchao Han , Jihong Park , Shiqiang Wang , Yejun Liu

Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downstream tasks. To address this limitation, this paper…

Machine Learning · Computer Science 2025-04-21 Wenxuan Yang , Qingqu Wei , Chenxi Ma , Weimin Tan , Bo Yan

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Junhong Liu , Yuan Zhang , Tao Huang , Wenchao Xu , Renyu Yang

Knowledge distillation (KD) is a powerful model compression technique broadly used in practical deep learning applications. It is focused on training a small student network to mimic a larger teacher network. While it is widely known that…

Machine Learning · Computer Science 2023-09-21 Valeriy Berezovskiy , Nikita Morozov

This work introduces a novel knowledge distillation framework for classification tasks where information on existing subclasses is available and taken into consideration. In classification tasks with a small number of classes or binary…

Machine Learning · Computer Science 2022-07-19 Ahmad Sajedi , Yuri A. Lawryshyn , Konstantinos N. Plataniotis

This study investigates the impact of gradient compression on distributed training performance, focusing on sparsification and quantization techniques, including top-k, DGC, and QSGD. In baseline experiments, random-k compression results in…

Machine Learning · Computer Science 2025-02-12 Shruti Singh , Shantanu Kumar

Grokking the delayed transition from memorization to generalization in neural networks remains poorly understood, in part because prior empirical studies confound the roles of architecture, optimization, and regularization. We present a…

Machine Learning · Computer Science 2026-03-27 Shalima Binta Manir , Anamika Paul Rupa

Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based methods have attracted attention for their high efficiency.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Fengli Ran , Xiao Pu , Bo Liu , Xiuli Bi , Bin Xiao

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Jialiang Tang , Shuo Chen , Gang Niu , Masashi Sugiyama , Chen Gong