English
Related papers

Related papers: Grokking in Linear Estimators -- A Solvable Model …

200 papers

Weak-to-strong generalization is a phenomenon in post-training whereby a strong student model, when finetuned solely with feedback from a weaker teacher, can not only surpass the teacher, but can improve upon its own capabilities. Recent…

Machine Learning · Computer Science 2026-05-08 Scott Geng , Dutch Hansen , Jerry Li

Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples, with evaluation largely driven by held-out performance and perceived sample quality. In…

Machine Learning · Computer Science 2026-03-05 Jerome Garnier-Brun , Luca Biggio , Davide Beltrame , Marc Mézard , Luca Saglietti

Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why…

Machine Learning · Statistics 2026-03-19 Nil Ayday , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar

Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this regime often yields improved…

Machine Learning · Computer Science 2026-04-22 Mario Tuci , Caner Korkmaz , Umut Şimşekli , Tolga Birdal

In this work, we demonstrate that a simple two-layer neural network with standard activation functions can learn an arbitrary word operation in any finite group, provided sufficient width is available and exhibits grokking while doing so.…

Machine Learning · Computer Science 2025-09-09 Maor Shutman , Oren Louidor , Ran Tessler

Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather than deeper understanding. This concern extends even to…

Computation and Language · Computer Science 2026-03-03 Qinyuan Wu , Soumi Das , Mahsa Amani , Bishwamittra Ghosh , Mohammad Aflah Khan , Krishna P. Gummadi , Muhammad Bilal Zafar

Models for learning probability distributions such as generative models and density estimators behave quite differently from models for learning functions. One example is found in the memorization phenomenon, namely the ultimate convergence…

Machine Learning · Statistics 2021-03-03 Hongkang Yang , Weinan E

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

Machine Learning · Computer Science 2020-05-04 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

In physics, complex systems are often simplified into minimal, solvable models that retain only the core principles. In machine learning, layerwise linear models (e.g., linear neural networks) act as simplified representations of neural…

Given a pair of models with similar training set performance, it is natural to assume that the model that possesses simpler internal representations would exhibit better generalization. In this work, we provide empirical evidence for this…

Machine Learning · Computer Science 2022-11-28 Bradley C. A. Brown , Jordan Juravsky , Anthony L. Caterini , Gabriel Loaiza-Ganem

Recent studies of generalization in deep learning have observed a puzzling trend: accuracies of models on one data distribution are approximately linear functions of the accuracies on another distribution. We explain this trend under an…

Machine Learning · Computer Science 2021-02-24 Horia Mania , Suvrit Sra

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

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

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

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

The majority of machine learning algorithms assumes that objects are represented as vectors. But often the objects we want to learn on are more naturally represented by other data structures such as sequences and time series. For these…

Machine Learning · Computer Science 2015-06-10 Brijnesh Jain

In the framework of on-line learning, a learning machine might move around a teacher due to the differences in structures or output functions between the teacher and the learning machine. In this paper we analyze the generalization…

Machine Learning · Computer Science 2009-11-11 Masahiro Urakami , Seiji Miyoshi , Masato Okada

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Machine Learning · Computer Science 2026-02-03 Simran Ketha , Venkatakrishnan Ramaswamy

Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitrarily long…

Machine Learning · Computer Science 2025-10-14 Ricardo Buitrago Ruiz , Albert Gu

Masked Diffusion Language Models have recently emerged as a powerful generative paradigm, yet their generalization properties remain understudied compared to their auto-regressive counterparts. In this work, we investigate these properties…

Machine Learning · Computer Science 2026-02-02 Jianhao Huang , Baharan Mirzasoleiman