English
Related papers

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

200 papers

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

Machine Learning · Statistics 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

With the growth of computing power neural machine translation (NMT) models also grow accordingly and become better. However, they also become harder to deploy on edge devices due to memory constraints. To cope with this problem, a common…

Computation and Language · Computer Science 2020-10-08 Yimeng Wu , Peyman Passban , Mehdi Rezagholizade , Qun Liu

The accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory…

Machine Learning · Statistics 2021-11-03 Pengzhan Jin , Lu Lu , Yifa Tang , George Em Karniadakis

Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Yuzhu Wang , Lechao Cheng , Manni Duan , Yongheng Wang , Zunlei Feng , Shu Kong

There has been considerable effort to better understand the generalization capabilities of deep neural networks both as a means to unlock a theoretical understanding of their success as well as providing directions for further improvements.…

Machine Learning · Statistics 2024-05-30 Michael Munn , Benoit Dherin , Javier Gonzalvo

We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide…

Computer Vision and Pattern Recognition · Computer Science 2018-09-10 Chenglin Yang , Lingxi Xie , Siyuan Qiao , Alan Yuille

While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial prefixes. The absence of class-discriminative patterns in partial data can significantly…

Machine Learning · Computer Science 2026-05-13 Nilushika Udayangani , Kishor Nandakishor , Marimuthu Palaniswami

The knowledge of a well-trained deep neural network (a.k.a. the "teacher") is valuable for learning similar tasks. Knowledge distillation extracts knowledge from the teacher and integrates it with the target model (a.k.a. the "student"),…

Computer Vision and Pattern Recognition · Computer Science 2022-05-05 Han-Jia Ye , Su Lu , De-Chuan Zhan

Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the NN is trained with Stochastic Gradient Descent (SGD) or one…

Machine Learning · Computer Science 2025-02-18 Gon Buzaglo , Itamar Harel , Mor Shpigel Nacson , Alon Brutzkus , Nathan Srebro , Daniel Soudry

Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network output side (e.g., trying to design a better KD loss function),…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Huan Wang , Suhas Lohit , Mike Jones , Yun Fu

An information-theoretic upper bound on the generalization error of supervised learning algorithms is derived. The bound is constructed in terms of the mutual information between each individual training sample and the output of the…

Machine Learning · Computer Science 2020-08-06 Yuheng Bu , Shaofeng Zou , Venugopal V. Veeravalli

Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Jaeyeon Jang , Young-Ik Kim , Jisu Lim , Hyeonseong Lee

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Deepan Das , Haley Massa , Abhimanyu Kulkarni , Theodoros Rekatsinas

Decision Focused Learning has emerged as a critical paradigm for integrating machine learning with downstream optimisation. Despite its promise, existing methodologies predominantly rely on probabilistic models and focus narrowly on task…

Machine Learning · Computer Science 2025-03-21 Keivan Shariatmadar , Neil Yorke-Smith , Ahmad Osman , Fabio Cuzzolin , Hans Hallez , David Moens

Much attention has been devoted recently to the generalization puzzle in deep learning: large, deep networks can generalize well, but existing theories bounding generalization error are exceedingly loose, and thus cannot explain this…

Machine Learning · Statistics 2019-01-08 Andrew K. Lampinen , Surya Ganguli

Knowledge distillation (KD) is a powerful strategy for training deep neural networks (DNNs). Although it was originally proposed to train a more compact "student" model from a large "teacher" model, many recent efforts have focused on…

Machine Learning · Computer Science 2025-05-20 Guanglong Sun , Hongwei Yan , Liyuan Wang , Qian Li , Bo Lei , Yi Zhong

We consider information-theoretic bounds on expected generalization error for statistical learning problems in a networked setting. In this setting, there are $K$ nodes, each with its own independent dataset, and the models from each node…

Information Theory · Computer Science 2024-01-17 L. P. Barnes , Alex Dytso , H. V. Poor

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry

Knowledge Distillation (KD) is a widespread technique for compressing the knowledge of large models into more compact and efficient models. KD has proved to be highly effective in building well-performing low-complexity Acoustic Scene…

Sound · Computer Science 2025-03-17 Tobias Morocutti , Florian Schmid , Khaled Koutini , Gerhard Widmer

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Yuang Liu , Wei Zhang , Jun Wang
‹ Prev 1 4 5 6 7 8 10 Next ›