English
Related papers

Related papers: Learning from Matured Dumb Teacher for Fine Genera…

200 papers

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various…

Machine Learning · Computer Science 2020-07-08 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Yuang Liu , Wei Zhang , Jun Wang

Does Knowledge Distillation (KD) really work? Conventional wisdom viewed it as a knowledge transfer procedure where a perfect mimicry of the student to its teacher is desired. However, paradoxical studies indicate that closely replicating…

Machine Learning · Computer Science 2024-05-03 Chenqi Guo , Shiwei Zhong , Xiaofeng Liu , Qianli Feng , Yinglong Ma

Knowledge Distillation (KD) could transfer the ``dark knowledge" of a well-performed yet large neural network to a weaker but lightweight one. From the view of output logits and softened probabilities, this paper goes deeper into the dark…

Machine Learning · Computer Science 2025-06-09 Wen-Shu Fan , Xin-Chun Li , De-Chuan Zhan

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Computation and Language · Computer Science 2023-11-08 Manas Mohanty , Tanya Roosta , Peyman Passban

Typical technique in knowledge distillation (KD) is regularizing the learning of a limited capacity model (student) by pushing its responses to match a powerful model's (teacher). Albeit useful especially in the penultimate layer and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Ada Gorgun , Yeti Z. Gurbuz , A. Aydin Alatan

We study the notion of a generalization bound being uniformly tight, meaning that the difference between the bound and the population loss is small for all learning algorithms and all population distributions. Numerous generalization bounds…

Machine Learning · Computer Science 2023-11-29 Michael Gastpar , Ido Nachum , Jonathan Shafer , Thomas Weinberger

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-27 Tiancheng Wen , Shenqi Lai , Xueming Qian

The paper establishes generalization bounds for multitask deep neural networks using operator-theoretic techniques. The authors propose a tighter bound than those derived from conventional norm based methods by leveraging small condition…

Machine Learning · Computer Science 2026-05-29 Mahdi Mohammadigohari , Giuseppe Di Fatta , Giuseppe Nicosia , Panos M. Pardalos

We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding of both the conventional learning-to-learn framework and the modern…

Machine Learning · Computer Science 2021-12-13 Qi Chen , Changjian Shui , Mario Marchand

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network…

Machine Learning · Computer Science 2023-12-15 Yi Guo , Yiqian He , Xiaoyang Li , Haotong Qin , Van Tung Pham , Yang Zhang , Shouda Liu

Deep neural networks generalize well despite being heavily overparameterized, in apparent contradiction with classical learning theory based on uniform convergence over fixed hypothesis spaces. Uniform bounds over the entire parameter space…

Machine Learning · Statistics 2026-05-15 Hubert Leroux , Jean Marcus , Julien Roger

This paper provides theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the…

Machine Learning · Statistics 2023-08-29 Kenji Kawaguchi , Leslie Pack Kaelbling , Yoshua Bengio

Deep neural networks have achieved remarkable performance for artificial intelligence tasks. The success behind intelligent systems often relies on large-scale models with high computational complexity and storage costs. The…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Chuanguang Yang , Xinqiang Yu , Zhulin An , Yongjun Xu

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Li Yuan , Francis E. H. Tay , Guilin Li , Tao Wang , Jiashi Feng

Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories…

Machine Learning · Computer Science 2019-12-02 Guanhua Zheng , Jitao Sang , Houqiang Li , Jian Yu , Changsheng Xu

Knowledge distillation is a strategy of training a student network with guide of the soft output from a teacher network. It has been a successful method of model compression and knowledge transfer. However, currently knowledge distillation…

Machine Learning · Computer Science 2024-10-21 Guangda Ji , Zhanxing Zhu

In recent years, information-theoretic generalization bounds have gained increasing attention for analyzing the generalization capabilities of meta-learning algorithms. However, existing results are confined to two-step bounds, failing to…

Machine Learning · Statistics 2025-10-14 Wen Wen , Tieliang Gong , Yuxin Dong , Zeyu Gao , Yong-Jin Liu

Knowledge distillation (KD) is a model compression method that entails training a compact student model to emulate the performance of a more complex teacher model. However, the architectural capacity gap between the two models limits the…

Machine Learning · Computer Science 2025-01-09 Kuluhan Binici , Weiming Wu , Tulika Mitra

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Jorge Gonzalez-Zapata , Ivan Reyes-Amezcua , Daniel Flores-Araiza , Mauricio Mendez-Ruiz , Gilberto Ochoa-Ruiz , Andres Mendez-Vazquez