English
Related papers

Related papers: Towards Understanding Inductive Bias in Transforme…

200 papers

Transformers, which are state-of-the-art in most machine learning tasks, represent the data as sequences of vectors called tokens. This representation is then exploited by the attention function, which learns dependencies between tokens and…

Machine Learning · Computer Science 2025-01-31 Valérie Castin , Pierre Ablin , José Antonio Carrillo , Gabriel Peyré

Transformers excel through content-addressable retrieval and the ability to exploit contexts of, in principle, unbounded length. We recast associative memory at the level of probability measures, treating a context as a distribution over…

Machine Learning · Statistics 2026-02-03 Ryotaro Kawata , Taiji Suzuki

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output dimension, and depth are kept fixed, while the hidden layer…

Probability · Mathematics 2021-07-06 Boris Hanin

Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How does such…

Machine Learning · Computer Science 2026-05-19 Afiq Abdillah Effiezal Aswadi , Oliver Britton , Ross Baker , Matthew Farrugia-Roberts

Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We develop a universal approximation theory to elucidate how…

Machine Learning · Computer Science 2025-08-29 Gen Li , Yuchen Jiao , Yu Huang , Yuting Wei , Yuxin Chen

Machine learning systems often acquire biases by leveraging undesired features in the data, impacting accuracy variably across different sub-populations. Current understanding of bias formation mostly focuses on the initial and final stages…

Machine Learning · Computer Science 2024-12-24 Anchit Jain , Rozhin Nobahari , Aristide Baratin , Stefano Sarao Mannelli

We study the implicit bias of gradient flow (i.e., gradient descent with infinitesimal step size) on linear neural network training. We propose a tensor formulation of neural networks that includes fully-connected, diagonal, and…

Machine Learning · Computer Science 2021-09-13 Chulhee Yun , Shankar Krishnan , Hossein Mobahi

The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural networks have…

Machine Learning · Computer Science 2025-04-21 Mircea Petrache , Shubhendu Trivedi

Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their superior results when dealing with multidimensional signals in…

Machine Learning · Computer Science 2024-05-14 Danilo Comminiello , Eleonora Grassucci , Danilo P. Mandic , Aurelio Uncini

Despite the recent success of artificial neural networks on a variety of tasks, we have little knowledge or control over the exact solutions these models implement. Instilling inductive biases -- preferences for some solutions over others…

Machine Learning · Computer Science 2024-02-02 Enyan Zhang , Michael A. Lepori , Ellie Pavlick

Sampling biases can cause distribution shifts between train and test datasets for supervised learning tasks, obscuring our ability to understand the generalization capacity of a model. This is especially important considering the wide…

Machine Learning · Computer Science 2024-02-05 Max Vargas , Adam Tsou , Andrew Engel , Tony Chiang

Strong inductive biases enable learning from little data and help generalization outside of the training distribution. Popular neural architectures such as Transformers lack strong structural inductive biases for seq2seq NLP tasks on their…

Computation and Language · Computer Science 2024-07-11 Matthias Lindemann , Alexander Koller , Ivan Titov

Transformers are deep architectures that define ``in-context maps'' which enable predicting new tokens based on a given set of tokens (such as a prompt in NLP applications or a set of patches for a vision transformer). In previous work, we…

Computation and Language · Computer Science 2025-10-01 Takashi Furuya , Maarten V. de Hoop , Matti Lassas

In this paper, we propose a data based transformation for infinite-dimensional Gaussian processes and derive its limit theorem. For a classification problem, this transformation induces complete separation among the associated Gaussian…

Statistics Theory · Mathematics 2022-03-25 Juan A. Cuesta-Albertos , Subhajit Dutta

One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize…

Machine Learning · Computer Science 2025-08-14 Jingwei Li , Jing Xu , Zifan Wang , Huishuai Zhang , Jingzhao Zhang

The inference of deep hierarchical models is problematic due to strong dependencies between the hierarchies. We investigate a specific transformation of the model parameters based on the multivariate distributional transform. This…

Machine Learning · Statistics 2018-12-12 Jakob Knollmüller , Torsten A. Enßlin

Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…

Machine Learning · Computer Science 2025-05-19 Omer Sahin Tas , Royden Wagner

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has…

Computation and Language · Computer Science 2022-03-24 Nathan Young , Qiming Bao , Joshua Bensemann , Michael Witbrock

Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Javier Selva , Anders S. Johansen , Sergio Escalera , Kamal Nasrollahi , Thomas B. Moeslund , Albert Clapés

Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge. While recent advancements have been made…

‹ Prev 1 3 4 5 6 7 10 Next ›