English
Related papers

Related papers: The Pitfalls of Memorization: When Memorization Hu…

200 papers

The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the…

Machine Learning · Computer Science 2021-10-22 Kaustubh Olpadkar , Ekta Gavas

Recent studies suggest that ``memorization'' is one important factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly fitted DNNs can memorize the labels of many atypical samples,…

Machine Learning · Computer Science 2021-06-10 Han Xu , Xiaorui Liu , Wentao Wang , Wenbiao Ding , Zhongqin Wu , Zitao Liu , Anil Jain , Jiliang Tang

We examine the connection between training error and generalization error for arbitrary estimating procedures, working in an overparameterized linear model under general priors in a Bayesian setup. We find determining factors inherent to…

Machine Learning · Statistics 2026-02-11 Chen Cheng , Rina Foygel Barber

Neural machine translation (NMT) models usually suffer from catastrophic forgetting during continual training where the models tend to gradually forget previously learned knowledge and swing to fit the newly added data which may have a…

Computation and Language · Computer Science 2020-12-01 Shuhao Gu , Yang Feng

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Machine Learning · Computer Science 2024-09-05 Eric Zhang , Leshem Chosen , Jacob Andreas

Public datasets are often used to evaluate the efficacy and generalizability of state-of-the-art methods for many tasks in natural language processing (NLP). However, the presence of overlap between the train and test datasets can lead to…

Computation and Language · Computer Science 2021-02-04 Aparna Elangovan , Jiayuan He , Karin Verspoor

The phenomenon of grokking in over-parameterized neural networks has garnered significant interest. It involves the neural network initially memorizing the training set with zero training error and near-random test error. Subsequent…

Machine Learning · Computer Science 2024-12-17 Hu Qiye , Zhou Hao , Yu RuoXi

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetting, making it impossible to perform life-long learning. To…

Machine Learning · Computer Science 2023-01-31 Longhui Yu , Tianyang Hu , Lanqing Hong , Zhen Liu , Adrian Weller , Weiyang Liu

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that…

Artificial Intelligence · Computer Science 2026-04-09 Qihan Ren , Peng Wang , Ruikun Cai , Shuai Shao , Dadi Guo , Yuejin Xie , Yafu Li , Quanshi Zhang , Xia Hu , Jing Shao , Dongrui Liu

This study aims to understand how statistical biases affect the model's ability to generalize to in-distribution and out-of-distribution data on algorithmic tasks. Prior research indicates that transformers may inadvertently learn to rely…

Machine Learning · Computer Science 2024-09-11 John Mitros

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural…

Machine Learning · Computer Science 2026-03-04 Max S. Bennett , Thomas P. Zollo , Richard Zemel

Neural networks can be powerful function approximators, which are able to model high-dimensional feature distributions from a subset of examples drawn from the target distribution. Naturally, they perform well at generalizing within the…

Machine Learning · Computer Science 2021-08-06 Aaron Eisermann , Jae Hee Lee , Cornelius Weber , Stefan Wermter

Neural networks are known to exploit spurious artifacts (or shortcuts) that co-occur with a target label, exhibiting heuristic memorization. On the other hand, networks have been shown to memorize training examples, resulting in…

Machine Learning · Computer Science 2024-02-05 Rachit Bansal , Danish Pruthi , Yonatan Belinkov

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Hannes Fassold

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Machine Learning · Computer Science 2020-11-23 Hrayr Harutyunyan , Kyle Reing , Greg Ver Steeg , Aram Galstyan

Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address different types of overfitting, typically designing…

Machine Learning · Computer Science 2024-09-17 Runqi Lin , Chaojian Yu , Bo Han , Tongliang Liu

Understanding how large neural networks avoid memorizing training data is key to explaining their high generalization performance. To examine the structure of when and where memorization occurs in a deep network, we use a recently developed…

Machine Learning · Computer Science 2021-06-01 Cory Stephenson , Suchismita Padhy , Abhinav Ganesh , Yue Hui , Hanlin Tang , SueYeon Chung

We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Byungju Kim , Hyunwoo Kim , Kyungsu Kim , Sungjin Kim , Junmo Kim

Domain generalization is the problem of machine learning when the training data and the test data come from different data domains. We present a simple theoretical model of learning to generalize across domains in which there is a…

Machine Learning · Computer Science 2020-02-14 Vikas K. Garg , Adam Kalai , Katrina Ligett , Zhiwei Steven Wu

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