English
Related papers

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

200 papers

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

Hypothesis-pruning maximizes the hypothesis updates for active learning to find those desired unlabeled data. An inherent assumption is that this learning manner can derive those updates into the optimal hypothesis. However, its convergence…

Machine Learning · Computer Science 2023-09-21 Xiaofeng Cao , Yaming Guo , Ivor W. Tsang , James T. Kwok

This paper explores the tasks of leveraging auxiliary modalities which are only available at training to enhance multimodal representation learning through cross-modal Knowledge Distillation (KD). The widely adopted mutual information…

Computer Vision and Pattern Recognition · Computer Science 2023-06-14 Mengxi Chen , Linyu Xing , Yu Wang , Ya Zhang

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data…

Machine Learning · Computer Science 2025-10-31 Jiali Cheng , Chirag Agarwal , Hadi Amiri

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased…

Machine Learning · Computer Science 2023-10-11 Bhavya Vasudeva , Kameron Shahabi , Vatsal Sharan

Knowledge distillation (KD) techniques have emerged as a powerful tool for transferring expertise from complex teacher models to lightweight student models, particularly beneficial for deploying high-performance models in…

Machine Learning · Computer Science 2025-10-28 Paul Agbaje , Arkajyoti Mitra , Afia Anjum , Pranali Khose , Ebelechukwu Nwafor , Habeeb Olufowobi

We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected networks. This framework resolves long-standing barriers to characterizing the rich nonlinear…

Machine Learning · Computer Science 2026-05-19 Shaojie Li , Yunbei Xu

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza

We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the…

Machine Learning · Computer Science 2019-04-25 Yonatan Geifman , Guy Uziel , Ran El-Yaniv

Recent research has used margin theory to analyze the generalization performance for deep neural networks (DNNs). The existed results are almost based on the spectrally-normalized minimum margin. However, optimizing the minimum margin…

Machine Learning · Computer Science 2024-07-10 Shen-Huan Lyu , Lu Wang , Zhi-Hua Zhou

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make…

Machine Learning · Computer Science 2022-11-02 Masud An-Nur Islam Fahim , Jani Boutellier

Along with the rapid development of deep learning in practice, the theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning.…

Machine Learning · Computer Science 2018-03-26 Shao-Bo Lin

Knowledge distillation (KD) has received much attention due to its success in compressing networks to allow for their deployment in resource-constrained systems. While the problem of adversarial robustness has been studied before in the KD…

Machine Learning · Computer Science 2023-08-14 Tom A. Lamb , Rudy Brunel , Krishnamurthy DJ Dvijotham , M. Pawan Kumar , Philip H. S. Torr , Francisco Eiras

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

Deep learning methods are known to generalize well from training to future data, even in an overparametrized regime, where they could easily overfit. One explanation for this phenomenon is that even when their *ambient dimensionality*,…

Machine Learning · Computer Science 2025-05-22 Hossein Zakerinia , Dorsa Ghobadi , Christoph H. Lampert

Deep neural networks (DNNs) generalize remarkably well without explicit regularization even in the strongly over-parametrized regime where classical learning theory would instead predict that they would severely overfit. While many…

Machine Learning · Statistics 2019-04-23 Guillermo Valle-Pérez , Chico Q. Camargo , Ard A. Louis

Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However, most KD methods require a large training set and internal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Tri-Nhan Vo , Dang Nguyen , Kien Do , Sunil Gupta

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural…

Machine Learning · Statistics 2022-03-28 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Conventional knowledge distillation, designed for model compression, fails on long-tailed distributions because the teacher model tends to be biased toward head classes and provides limited supervision for tail classes. We propose…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Seonghak Kim

The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient…

Machine Learning · Computer Science 2022-08-16 Manzil Zaheer , Ankit Singh Rawat , Seungyeon Kim , Chong You , Himanshu Jain , Andreas Veit , Rob Fergus , Sanjiv Kumar