English
Related papers

Related papers: Grokking and Generalization Collapse: Insights fro…

200 papers

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Modern deep neural networks for classification usually jointly learn a backbone for representation and a linear classifier to output the logit of each class. A recent study has shown a phenomenon called neural collapse that the within-class…

Machine Learning · Computer Science 2022-10-13 Yibo Yang , Shixiang Chen , Xiangtai Li , Liang Xie , Zhouchen Lin , Dacheng Tao

This paper presents a neural network filter method based on contraction operators to address model collapse in recursive training of generative models. Unlike \cite{xu2024probabilistic}, which requires superlinear sample growth…

Machine Learning · Computer Science 2025-12-02 Zongjian Han , Yiran Liang , Ruiwen Wang , Yiwei Luo , Yilin Huang , Xiaotong Song , Dongqing Wei

Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multiple layers and the node representations in each layer are…

Machine Learning · Computer Science 2020-09-25 Yihao Chen , Xin Tang , Xianbiao Qi , Chun-Guang Li , Rong Xiao

A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infinity, the NN training dynamics converge in probability to…

Machine Learning · Computer Science 2026-05-21 Konstantin Riedl , Konstantinos Spiliopoulos , Justin Sirignano

Hardness of approximation (HA) -- the phenomenon that, assuming P $\neq$ NP, one can easily compute an $\epsilon$-approximation to the solution of a discrete computational problem for $\epsilon > \epsilon_0 > 0$, but for $\epsilon <…

Optimization and Control · Mathematics 2023-01-04 Luca Eva Gazdag , Anders C. Hansen

Modern large language models (LLMs) are increasingly fine-tuned via reinforcement learning from human feedback (RLHF) or related reward optimisation schemes. While such procedures improve perceived helpfulness, we investigate whether…

Machine Learning · Computer Science 2026-04-14 Subramanyam Sahoo

Recent studies have uncovered intriguing phenomena in deep learning, such as grokking, double descent, and emergent abilities in large language models, which challenge human intuition and are crucial for a deeper understanding of neural…

Machine Learning · Computer Science 2024-02-27 Yufei Huang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

Graph Neural Networks (GNNs) struggle to balance heterophily and homophily in representation learning, a challenge further amplified in self-supervised settings. We propose H$^3$GNNs, an end-to-end self-supervised learning framework that…

Machine Learning · Computer Science 2025-04-17 Rui Xue , Tianfu Wu

Recent years have witnessed the huge success of deep neural networks (DNNs) in various tasks of computer vision and text processing. Interestingly, these DNNs with massive number of parameters share similar structural properties on their…

Machine Learning · Statistics 2023-10-26 Wanli Hong , Shuyang Ling

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive…

Machine Learning · Computer Science 2026-04-15 Qinghua Zhao , Xueling Gong , Xinyu Chen , Zhongfeng Kang , Xinlu Li

The deployment of large language models (LLMs) is largely hindered by their large number of parameters. Structural pruning has emerged as a promising solution. Prior structured pruning methods directly remove unimportant parameters based on…

Machine Learning · Computer Science 2026-04-21 Mingkuan Feng , Jinyang Wu , Siyuan Liu , Shuai Zhang , Hongjian Fang , Ruihan Jin , Feihu Che , Pengpeng Shao , Zhengqi Wen , Jianhua Tao

Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on…

Machine Learning · Computer Science 2023-10-27 Vignesh Kothapalli , Tom Tirer , Joan Bruna

In this paper, we give a new generalization error bound of Multiple Kernel Learning (MKL) for a general class of regularizations, and discuss what kind of regularization gives a favorable predictive accuracy. Our main target in this paper…

Machine Learning · Statistics 2011-11-17 Taiji Suzuki

Graph convolutional networks (GCNs) have recently achieved great empirical success in learning graph-structured data. To address its scalability issue due to the recursive embedding of neighboring features, graph topology sampling has been…

Machine Learning · Computer Science 2023-12-12 Hongkang Li , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its impact has been extensively studied under the asymptotic…

Machine Learning · Computer Science 2026-05-27 Taesun Yeom , Taehyeok Ha , Jaeho Lee

We study the optimization of wide neural networks (NNs) via gradient flow (GF) in setups that allow feature learning while admitting non-asymptotic global convergence guarantees. First, for wide shallow NNs under the mean-field scaling and…

Machine Learning · Computer Science 2022-04-25 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for regularization. While deep transfer learning can usually…

Machine Learning · Computer Science 2019-11-19 Ruosi Wan , Haoyi Xiong , Xingjian Li , Zhanxing Zhu , Jun Huan

This paper is devoted to the performance analysis of the detectors proposed in the companion paper where a comprehensive design framework is presented for the adaptive detection of subspace signals. The framework addresses four variations…

Signal Processing · Electrical Eng. & Systems 2022-11-23 Pia Addabbo , Danilo Orlando , Giuseppe Ricci , Louis L. Scharf

Existing accounts of grokking explain the phenomena in terms of mechanistic frameworks such as circuit efficiency or lazy-to-rich transitions. However, despite a known dependence between grokking and model size, how model capacity shapes…

Machine Learning · Computer Science 2026-05-12 Yiding Song , Hanming Ye
‹ Prev 1 8 9 10 Next ›