English
Related papers

Related papers: Length Generalization Bounds for Transformers

200 papers

Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous for large models at…

Machine Learning · Statistics 2024-07-26 Sanae Lotfi , Yilun Kuang , Brandon Amos , Micah Goldblum , Marc Finzi , Andrew Gordon Wilson

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

The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages. Despite impressive empirical results and an…

Machine Learning · Computer Science 2020-08-12 Han Zhao , Junjie Hu , Andrej Risteski

We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm. These bounds improve over the existing…

Machine Learning · Computer Science 2021-10-06 Hrayr Harutyunyan , Maxim Raginsky , Greg Ver Steeg , Aram Galstyan

This paper is motivated by an open problem around deep networks, namely, the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we analyze this phenomenon in…

Machine Learning · Computer Science 2019-08-28 Hrushikesh Mhaskar , Tomaso Poggio

We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalability of machine learning systems in a realistic compositional…

Machine Learning · Computer Science 2020-12-16 Dmitry Tsarkov , Tibor Tihon , Nathan Scales , Nikola Momchev , Danila Sinopalnikov , Nathanael Schärli

What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of…

Computation and Language · Computer Science 2025-01-14 Nadav Borenstein , Anej Svete , Robin Chan , Josef Valvoda , Franz Nowak , Isabelle Augenstein , Eleanor Chodroff , Ryan Cotterell

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Computation and Language · Computer Science 2025-11-14 Benjamin L. Badger , Matthew Neligeorge

Along with the rapid development of deep learning in practice, the theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning.…

Machine Learning · Computer Science 2018-03-26 Shao-Bo Lin

This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a duality between…

Machine Learning · Statistics 2022-07-01 Eugenio Clerico , Amitis Shidani , George Deligiannidis , Arnaud Doucet

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these…

Machine Learning · Computer Science 2025-10-24 Mayank Jobanputra , Yana Veitsman , Yash Sarrof , Aleksandra Bakalova , Vera Demberg , Ellie Pavlick , Michael Hahn

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the…

Machine Learning · Computer Science 2023-11-01 Jingwen Fu , Zhizheng Zhang , Dacheng Yin , Yan Lu , Nanning Zheng

The general intractability of the constraint satisfaction problem has motivated the study of restrictions on this problem that permit polynomial-time solvability. One major line of work has focused on structural restrictions, which arise…

Computational Complexity · Computer Science 2007-05-23 Hubie Chen , Victor Dalmau

The dependency of the generalization error of neural networks on model and dataset size is of critical importance both in practice and for understanding the theory of neural networks. Nevertheless, the functional form of this dependency…

Machine Learning · Computer Science 2019-12-23 Jonathan S. Rosenfeld , Amir Rosenfeld , Yonatan Belinkov , Nir Shavit

We investigate the parameterized complexity of Bayesian Network Structure Learning (BNSL), a classical problem that has received significant attention in empirical but also purely theoretical studies. We follow up on previous works that…

Data Structures and Algorithms · Computer Science 2026-02-12 Robert Ganian , Viktoriia Korchemna

The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance,…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Lin Song , Yanwei Li , Zhengkai Jiang , Zeming Li , Xiangyu Zhang , Hongbin Sun , Jian Sun , Nanning Zheng

In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being…

Machine Learning · Statistics 2019-07-30 Anastasia Borovykh , Cornelis W. Oosterlee , Sander M. Bohte

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

Built upon the Transformer, large language models (LLMs) have captured worldwide attention due to their remarkable abilities. Nevertheless, all Transformer-based models including LLMs suffer from a preset length limit and can hardly…

Computation and Language · Computer Science 2024-10-08 Liang Zhao , Xiachong Feng , Xiaocheng Feng , Weihong Zhong , Dongliang Xu , Qing Yang , Hongtao Liu , Bing Qin , Ting Liu

Large language models often struggle with length generalization and solving complex problem instances beyond their training distribution. We present a self-improvement approach where models iteratively generate and learn from their own…

Machine Learning · Computer Science 2025-02-14 Nayoung Lee , Ziyang Cai , Avi Schwarzschild , Kangwook Lee , Dimitris Papailiopoulos