English
Related papers

Related papers: Bigger Isn't Always Memorizing: Early Stopping Ove…

200 papers

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

In this paper, we introduce a geometric framework to analyze memorization in diffusion models through the sharpness of the log probability density. We mathematically justify a previously proposed score-difference-based memorization metric…

Machine Learning · Computer Science 2025-08-20 Dongjae Jeon , Dueun Kim , Albert No

Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising score matching--leads to memorization, where generated samples…

Machine Learning · Statistics 2025-05-07 Yu-Han Wu , Pierre Marion , Gérard Biau , Claire Boyer

Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have emerged as a promising alternative, though their advantages…

Machine Learning · Computer Science 2025-10-28 Mihir Prabhudesai , Mengning Wu , Amir Zadeh , Katerina Fragkiadaki , Deepak Pathak

We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated samples go relative to the geometry induced by the data? To answer this, we introduce a…

Machine Learning · Statistics 2026-05-14 Ye He , Yitong Qiu , Molei Tao

Diffusion Models represent a significant advancement in generative modeling, employing a dual-phase process that first degrades domain-specific information via Gaussian noise and restores it through a trainable model. This framework enables…

Neural and Evolutionary Computing · Computer Science 2024-11-21 Benedikt Hartl , Yanbo Zhang , Hananel Hazan , Michael Levin

Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise. While these models have enjoyed great success recently, a full theoretical…

Machine Learning · Computer Science 2023-09-22 Raja Marjieh , Ilia Sucholutsky , Thomas A. Langlois , Nori Jacoby , Thomas L. Griffiths

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

The generative adversarial network (GAN) is a well-known model for learning high-dimensional distributions, but the mechanism for its generalization ability is not understood. In particular, GAN is vulnerable to the memorization phenomenon,…

Machine Learning · Computer Science 2026-02-18 Hongkang Yang , Weinan E

Imitation learning holds the promise of equipping robots with versatile skills by learning from expert demonstrations. However, policies trained on finite datasets often struggle to generalize beyond the training distribution. In this work,…

Machine Learning · Computer Science 2025-04-28 Yixiao Wang

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

Machine learning traditionally assumes that the training and testing data are distributed independently and identically. However, in many real-world settings, the data distribution can shift over time, leading to poor generalization of…

Machine Learning · Computer Science 2024-02-19 Sepidehsadat Hosseini , Mengyao Zhai , Hossein Hajimirsadegh , Frederick Tung

Large Language Models (LLMs) demonstrate strong few-shot generalization through in-context learning, yet their reasoning in dynamic and stochastic environments remains opaque. Prior studies mainly focus on static tasks and overlook the…

Artificial Intelligence · Computer Science 2025-12-23 Jensen Zhang , Jing Yang , Keze Wang

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates extended training periods and may potentially impede modeling flexibility and capacity. To counteract…

Machine Learning · Computer Science 2023-06-06 Etrit Haxholli , Marco Lorenzi

Large Language Models (LLMs) are typically trained on data mixtures: most data come from web scrapes, while a small portion is curated from high-quality sources with dense domain-specific knowledge. In this paper, we show that when training…

Machine Learning · Computer Science 2026-05-12 Xinran Gu , Kaifeng Lyu , Jiazheng Li , Jingzhao Zhang

Learned priors based on deep generative models offer data-driven regularization for seismic inversion, but training them requires a dataset of representative subsurface models -- a resource that is inherently scarce in geoscience…

Machine Learning · Statistics 2026-03-23 Ali Siahkoohi , Davide Sabeddu

The new paradigm of test-time scaling has yielded remarkable breakthroughs in Large Language Models (LLMs) (e.g. reasoning models) and in generative vision models, allowing models to allocate additional computation during inference to…

Machine Learning · Computer Science 2025-08-14 Luca Eyring , Shyamgopal Karthik , Alexey Dosovitskiy , Nataniel Ruiz , Zeynep Akata

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

Deep networks have been known to have extraordinary generalization abilities, via mechanisms that aren't yet well understood. It is also known that upon shuffling labels in the training data to varying degrees, deep networks, trained with…

Machine Learning · Computer Science 2026-03-23 Simran Ketha , Venkatakrishnan Ramaswamy
‹ Prev 1 4 5 6 7 8 10 Next ›