The paper investigates how knowledge distillation (KD) applied at intermediate layers of a neural network can affect overfitting and model performance. While traditional KD focuses on the final output, this study explores block‑wise KD across eleven datasets, finding that on standard datasets the last block suffices, but on fine‑grained, data‑scarce settings intermediate supervision significantly improves accuracy. The authors also analyze optimal supervision granularity using attention maps, Centered Kernel Alignment, and Grad‑CAM, and examine teacher‑student fine‑tuning strategies.
By Irene Trigueros-Lorca, Leonardo Concepci\'on, Christian Wagner, Isaac Triguero, Daniel Molina
arXiv:2311. 02960v5 Announce Type: replace Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data.
By Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu
arXiv:2606. 00130v2 Announce Type: replace-cross Abstract: Large deep neural networks are costly to store and deploy because inference must move and evaluate many parameters.
By Andrzej Cichocki, Michal Wietczak
The paper introduces a pointwise generalization theory for fully connected deep neural networks, using a pointwise Riemannian Dimension derived from eigenvalues of learned feature representations across layers. This framework provides hypothesis-dependent, representation-aware generalization bounds that are significantly tighter than traditional size- or norm-based approaches, both theoretically and experimentally. The authors analytically identify structural properties that explain deep networks’ tractability and empirically show that the pointwise Riemannian Dimension captures feature compression, over‑parameterization effects, and optimizer bias.
By Shaojie Li, Yunbei Xu
arXiv:2604. 15613v4 Announce Type: replace-cross Abstract: We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation.
By Wladimir Silva
arXiv:2606. 18209v1 Announce Type: new Abstract: Dataset distillation (DD) has emerged as a prominent approach in data centric machine learning, aiming to synthesize compact training sets for efficient training by compressing the information in large datasets into a small number of synthetic samples.
By Trisha Mittal, Akshay Mehra, Joshua Kimball
arXiv:2607. 13432v1 Announce Type: new Abstract: Plasticity -- a neural network's ability to adapt to new tasks -- is critical for continual and transfer learning.
By Jiaxuan Cheng
arXiv:2607. 06796v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing.
By Javidan Abdullayev, Maxime Devanne, Jonathan Weber, Germain Forestier
arXiv:2603. 25144v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks.
By Hongxu Ma, Guang Li, Shijie Wang, Dongzhan Zhou, Baoli Sun, Takahiro Ogawa, Miki Haseyama, Zhihui Wang
arXiv:2603.25579v2 Announce Type: replace-cross
Abstract: A key capability of modern neural networks is their capacity to simultaneously learn underlying rules and memorize specific facts or exceptio...
By Gabriele Farn\'e, Fabrizio Boncoraglio, Lenka Zdeborov\'a
arXiv:2607. 15919v1 Announce Type: cross Abstract: Data-free knowledge distillation transfers the knowledge encoded in a teacher model to a student model without access to the original training data.
By Mohamed Amine Kina
arXiv:2506. 14202v4 Announce Type: replace-cross Abstract: End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability.
By Makoto Shing, Masanori Koyama, Takuya Akiba