English
Related papers

Related papers: Slower Generalization, Faster Memorization: A Swee…

200 papers

In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions,…

Machine Learning · Computer Science 2019-07-18 Simon Guiroy , Vikas Verma , Christopher Pal

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

Computation and Language · Computer Science 2024-10-10 Bozhou Li , Hao Liang , Yang Li , Fangcheng Fu , Hongzhi Yin , Conghui He , Wentao Zhang

Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the next-token in a sequence, with reinforcement learning…

Machine Learning · Computer Science 2025-12-18 Nikolaos Tsilivis , Eran Malach , Karen Ullrich , Julia Kempe

Grokking -- the abrupt transition from memorization to generalization long after near-zero training loss -- has been studied mainly in single-task settings. We extend geometric analysis to multi-task modular arithmetic, training…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

Graphical models with change-points are computationally challenging to fit, particularly in cases where the number of observation points and the number of nodes in the graph are large. Focusing on Gaussian graphical models, we introduce an…

Methodology · Statistics 2017-07-17 Yves Atchade , Leland Bybee

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on…

The learning properties of finite size polynomial Support Vector Machines are analyzed in the case of realizable classification tasks. The normalization of the high order features acts as a squeezing factor, introducing a strong anisotropy…

Disordered Systems and Neural Networks · Physics 2009-10-31 Sebastian Risau-Gusman , Mirta B. Gordon

In this paper, we are concerned with the generalization performance of non-parametric estimation for pairwise learning. Most of the existing work requires the hypothesis space to be convex or a VC-class, and the loss to be convex. However,…

Machine Learning · Statistics 2026-02-12 Junyu Zhou , Shuo Huang , Han Feng , Puyu Wang , Ding-Xuan Zhou

Convergence and generalization are two crucial aspects of performance in neural networks. When analyzed separately, these properties may lead to contradictory results. Optimizing a convergence rate yields fast training, but does not…

Machine Learning · Computer Science 2024-10-28 Ilona Kulikovskikh , Tarzan Legović

It has been shown \citep{broeck90:physicalreview,patarnello87:europhys} that feedforward Boolean networks can learn to perform specific simple tasks and generalize well if only a subset of the learning examples is provided for learning.…

Neural and Evolutionary Computing · Computer Science 2019-11-12 Alireza Goudarzi , Christof Teuscher , Natali Gulbahce , Thimo Rohlf

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

Machine Learning · Computer Science 2020-06-16 Daniel Chiu , Franklyn Wang , Scott Duke Kominers

For humans, language production and comprehension is sensitive to the hierarchical structure of sentences. In natural language processing, past work has questioned how effectively neural sequence models like transformers capture this…

Computation and Language · Computer Science 2023-05-31 Shikhar Murty , Pratyusha Sharma , Jacob Andreas , Christopher D. Manning

Inferring cluster structure in microarray datasets is a fundamental task for the -omic sciences. A fundamental question in Statistics, Data Analysis and Classification, is the prediction of the number of clusters in a dataset, usually…

Data Structures and Algorithms · Computer Science 2011-02-16 Filippo Utro

We investigate grokking in transformers through the lens of inductive bias: dispositions arising from architecture or optimization that let the network prefer one solution over another. We first show that architectural choices such as the…

Machine Learning · Computer Science 2026-02-09 Jaisidh Singh , Diganta Misra , Antonio Orvieto

Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detection, and molecular…

Machine Learning · Computer Science 2026-05-22 Mridul Gupta , Samyak Jain , Vansh Ramani , Hariprasad Kodamana , Sayan Ranu

Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by…

Computation and Language · Computer Science 2019-04-30 Hitomi Yanaka , Koji Mineshima , Daisuke Bekki , Kentaro Inui , Satoshi Sekine , Lasha Abzianidze , Johan Bos

Generative models have recently been explored for synthesizing neural network weights. These approaches take neural network checkpoints as training data and aim to generate high-performing weights during inference. In this work, we examine…

Machine Learning · Computer Science 2025-10-06 Boya Zeng , Yida Yin , Zhiqiu Xu , Zhuang Liu

We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner…

Machine Learning · Computer Science 2020-01-10 Eunbyung Park , Junier B. Oliva

In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained to interpolate the…

Machine Learning · Computer Science 2018-06-18 Siyuan Ma , Raef Bassily , Mikhail Belkin

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

Computer Vision and Pattern Recognition · Computer Science 2015-03-06 Xiangxin Zhu , Carl Vondrick , Charless Fowlkes , Deva Ramanan