English
Related papers

Related papers: Location Attention for Extrapolation to Longer Seq…

200 papers

Transformer language models have demonstrated impressive generalization capabilities in natural language domains, yet we lack a fine-grained understanding of how such generalization arises. In this paper, we investigate length…

Computation and Language · Computer Science 2025-08-05 Ziyang Cai , Nayoung Lee , Avi Schwarzschild , Samet Oymak , Dimitris Papailiopoulos

Long sequences occur in abundance within real-world scenarios, hence properly modelling them opens numerous down-stream use-cases. Deep neural networks, however, have often struggled with these for a variety of reasons. Recent advances,…

Machine Learning · Computer Science 2025-05-23 Jerry Huang

In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capacity of a neural network architecture: the largest number of…

Machine Learning · Statistics 2024-12-09 Sjoerd Dirksen , Patrick Finke , Martin Genzel

In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer…

Machine Learning · Computer Science 2024-07-22 Juliette Decugis , Alicia Y. Tsai , Max Emerling , Ashwin Ganesh , Laurent El Ghaoui

Despite -- or maybe because of -- their astonishing capacity to fit data, neural networks are believed to have difficulties extrapolating beyond training data distribution. This work shows that, for extrapolations based on finite…

Machine Learning · Computer Science 2021-04-21 S Chandra Mouli , Bruno Ribeiro

Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in…

Computation and Language · Computer Science 2022-04-20 Belen Alastruey , Javier Ferrando , Gerard I. Gállego , Marta R. Costa-jussà

In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural…

Machine Learning · Computer Science 2016-10-11 Georg Martius , Christoph H. Lampert

We study the generalization of over-parameterized deep networks (for image classification) in relation to the convex hull of their training sets. Despite their great success, generalization of deep networks is considered a mystery. These…

Machine Learning · Computer Science 2022-03-22 Roozbeh Yousefzadeh

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Computation and Language · Computer Science 2023-07-20 Jiayu Ding , Shuming Ma , Li Dong , Xingxing Zhang , Shaohan Huang , Wenhui Wang , Nanning Zheng , Furu Wei

The notion of interpolation and extrapolation is fundamental in various fields from deep learning to function approximation. Interpolation occurs for a sample $x$ whenever this sample falls inside or on the boundary of the given dataset's…

Machine Learning · Computer Science 2021-11-02 Randall Balestriero , Jerome Pesenti , Yann LeCun

The remarkable progress in deep learning in recent years is largely driven by improvements in scale, where bigger models are trained on larger datasets for longer schedules. To predict the benefit of scale empirically, we argue for a more…

Machine Learning · Computer Science 2022-11-02 Ibrahim Alabdulmohsin , Behnam Neyshabur , Xiaohua Zhai

The learning of the simplest possible computational pattern -- periodicity -- is an open problem in the research of strong generalisation in neural networks. We formalise the problem of extrapolative generalisation for periodic signals and…

Machine Learning · Computer Science 2022-09-22 Peter Belcák , Roger Wattenhofer

Machine learning systems, especially with overparameterized deep neural networks, can generalize to novel test instances drawn from the same distribution as the training data. However, they fare poorly when evaluated on out-of-support test…

Machine Learning · Computer Science 2023-04-28 Aviv Netanyahu , Abhishek Gupta , Max Simchowitz , Kaiqing Zhang , Pulkit Agrawal

Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer structural dependencies without abandoning end-to-end training.…

Computation and Language · Computer Science 2017-02-17 Yoon Kim , Carl Denton , Luong Hoang , Alexander M. Rush

Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental challenges in machine…

Machine Learning · Computer Science 2025-02-10 Niccolò Grillo , Andrea Toccaceli , Joël Mathys , Benjamin Estermann , Stefania Fresca , Roger Wattenhofer

Length Generalization is the essential capacity of autonomous agents to perform tasks in longer contexts than those encountered during training. To systematically study this feat, we test how well models can approximate the next token…

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

Recently, non-recurrent architectures (convolutional, self-attentional) have outperformed RNNs in neural machine translation. CNNs and self-attentional networks can connect distant words via shorter network paths than RNNs, and it has been…

Computation and Language · Computer Science 2018-11-13 Gongbo Tang , Mathias Müller , Annette Rios , Rico Sennrich

Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying…

Computation and Language · Computer Science 2022-01-04 Dušan Variš , Ondřej Bojar

Attention has become the core building block of modern machine learning (ML) by efficiently capturing the long-range dependencies among input tokens. Its inherently parallelizable structure allows for efficient performance scaling with the…

Machine Learning · Statistics 2026-02-27 Zhenyu Liao , Jiaqing Liu , TianQi Hou , Difan Zou , Zenan Ling