English
Related papers

Related papers: Grokking Explained: A Statistical Phenomenon

200 papers

Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the training of accurate neural models. Its applications span…

Machine Learning · Computer Science 2025-02-04 Saeed Vahidian , Mingyu Wang , Jianyang Gu , Vyacheslav Kungurtsev , Wei Jiang , Yiran Chen

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the…

Machine Learning · Computer Science 2017-02-28 Chiyuan Zhang , Samy Bengio , Moritz Hardt , Benjamin Recht , Oriol Vinyals

We derive a differential equation that governs the evolution of the generalization gap when a deep network is trained by gradient descent. This differential equation is controlled by two quantities, a contraction factor that brings together…

Machine Learning · Computer Science 2025-10-14 Rubing Yang , Pratik Chaudhari

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee

Ensembling is among the most popular tools in machine learning (ML) due to its effectiveness in minimizing variance and thus improving generalization. Most ensembling methods for black-box base learners fall under the umbrella of "stacked…

Machine Learning · Computer Science 2025-12-17 Hilaf Hasson , Danielle C. Maddix , Yuyang Wang , Gaurav Gupta , Youngsuk Park

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

Computer Vision and Pattern Recognition · Computer Science 2018-09-10 Tianyang Wang , Jun Huan , Bo Li

Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not…

Distribution shifts are common in real-world datasets and can affect the performance and reliability of deep learning models. In this paper, we study two types of distribution shifts: diversity shifts, which occur when test samples exhibit…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Alceu Bissoto , Catarina Barata , Eduardo Valle , Sandra Avila

Symbolic regression algorithms search a space of mathematical expressions for formulas that explain given data. Transformer-based models have emerged as a promising, scalable approach shifting the expensive combinatorial search to a…

Machine Learning · Computer Science 2025-09-25 Henrik Voigt , Paul Kahlmeyer , Kai Lawonn , Michael Habeck , Joachim Giesen

Continual learning, focused on sequentially learning multiple tasks, has gained significant attention recently. Despite the tremendous progress made in the past, the theoretical understanding, especially factors contributing to catastrophic…

Machine Learning · Computer Science 2024-05-29 Meng Ding , Kaiyi Ji , Di Wang , Jinhui Xu

We aim to determine some physical properties of distant galaxies (for example, stellar mass, star formation history, or chemical enrichment history) from their observed spectra, using supervised machine learning methods. We know that…

Instrumentation and Methods for Astrophysics · Physics 2020-12-02 Viviana Acquaviva , Chistopher Lovell , Emille Ishida

Graph Convolutional Networks (GCNs) have achieved impressive empirical advancement across a wide variety of semi-supervised node classification tasks. Despite their great success, training GCNs on large graphs suffers from computational and…

Machine Learning · Computer Science 2021-11-02 Weilin Cong , Morteza Ramezani , Mehrdad Mahdavi

Neural networks readily learn a subset of the modular arithmetic tasks, while failing to generalize on the rest. This limitation remains unmoved by the choice of architecture and training strategies. On the other hand, an analytical…

Machine Learning · Computer Science 2024-06-06 Darshil Doshi , Tianyu He , Aritra Das , Andrey Gromov

Weak-to-Strong Generalization (Burns et al., 2024) is the phenomenon whereby a strong student, say GPT-4, learns a task from a weak teacher, say GPT-2, and ends up significantly outperforming the teacher. We show that this phenomenon does…

Machine Learning · Computer Science 2025-11-11 Marko Medvedev , Kaifeng Lyu , Dingli Yu , Sanjeev Arora , Zhiyuan Li , Nathan Srebro

Generalization beyond the training distribution is a core challenge in machine learning. The common practice of mixing and shuffling examples when training neural networks may not be optimal in this regard. We show that partitioning the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Damien Teney , Ehsan Abbasnejad , Anton van den Hengel

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…

Machine Learning · Computer Science 2023-05-30 Chenyu Zheng , Guoqiang Wu , Chongxuan Li

It is becoming increasingly common in regression to train neural networks that model the entire distribution even if only the mean is required for prediction. This additional modeling often comes with performance gain and the reasons behind…

Machine Learning · Computer Science 2024-10-22 Ehsan Imani , Kai Luedemann , Sam Scholnick-Hughes , Esraa Elelimy , Martha White

This study investigates the impact of gradient compression on distributed training performance, focusing on sparsification and quantization techniques, including top-k, DGC, and QSGD. In baseline experiments, random-k compression results in…

Machine Learning · Computer Science 2025-02-12 Shruti Singh , Shantanu Kumar

This paper first answers the question "why do the two most powerful techniques Dropout and Batch Normalization (BN) often lead to a worse performance when they are combined together?" in both theoretical and statistical aspects.…

Machine Learning · Computer Science 2018-01-17 Xiang Li , Shuo Chen , Xiaolin Hu , Jian Yang

We propose a combinatorial and graph-theoretic theory of dropout by modeling training as a random walk over a high-dimensional graph of binary subnetworks. Each node represents a masked version of the network, and dropout induces stochastic…

Machine Learning · Computer Science 2025-05-30 Sahil Rajesh Dhayalkar