English
Related papers

Related papers: On the Expressive Power of Transformers for Maxout…

200 papers

Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains. But for some specific symmetries, representations, and choice of coordinates, the most common point-wise activations,…

Machine Learning · Computer Science 2024-01-18 Marco Pacini , Xiaowen Dong , Bruno Lepri , Gabriele Santin

This paper provides a theoretical justification of the superior classification performance of deep rectifier networks over shallow rectifier networks from the geometrical perspective of piecewise linear (PWL) classifier boundaries. We show…

Machine Learning · Computer Science 2017-08-25 Senjian An , Mohammed Bennamoun , Farid Boussaid

We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However,…

Machine Learning · Computer Science 2019-12-17 Thiago Serra , Srikumar Ramalingam

In this paper, we have extended the well-established universal approximator theory to neural networks that use the unbounded ReLU activation function and a nonlinear softmax output layer. We have proved that a sufficiently large neural…

Machine Learning · Computer Science 2020-02-12 Behnam Asadi , Hui Jiang

Previous research has explored the computational expressivity of Transformer models in simulating Boolean circuits or Turing machines. However, the learnability of these simulators from observational data has remained an open question. Our…

Machine Learning · Computer Science 2025-10-27 Morris Yau , Ekin Akyürek , Jiayuan Mao , Joshua B. Tenenbaum , Stefanie Jegelka , Jacob Andreas

Vision-Transformers are widely used in various vision tasks. Meanwhile, there is another line of works starting with the MLP-mixer trying to achieve similar performance using mlp-based architectures. Interestingly, until now those mlp-based…

Computation and Language · Computer Science 2022-11-18 Dan Navon , Alex M. Bronstein

This study explores the number of neurons required for a Rectified Linear Unit (ReLU) neural network to approximate multivariate monomials. We establish an exponential lower bound on the complexity of any shallow network approximating the…

Machine Learning · Computer Science 2023-05-17 Itai Shapira

The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitative approximation rates for ReLU networks on the class of…

Machine Learning · Computer Science 2026-04-17 Jonathan W. Siegel , Snir Hordan , Hannah Lawrence , Ali Syed , Nadav Dym

The expressiveness of deep neural network (DNN) is a perspective to understandthe surprising performance of DNN. The number of linear regions, i.e. pieces thata piece-wise-linear function represented by a DNN, is generally used to…

Machine Learning · Computer Science 2020-12-09 Yutong Xie , Gaoxiang Chen , Quanzheng Li

Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models…

Machine Learning · Statistics 2026-03-19 Nil Ayday , Lingchu Yang , Debarghya Ghoshdastidar

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and…

Machine Learning · Computer Science 2025-10-24 David Demitri Africa , Sara M. Kapoor , Theo Simon Sorg , Challenger Mishra

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies…

Computer Vision and Pattern Recognition · Computer Science 2022-01-20 Salman Khan , Muzammal Naseer , Munawar Hayat , Syed Waqas Zamir , Fahad Shahbaz Khan , Mubarak Shah

Transformers are the basis of modern large language models, but relatively little is known about their precise expressive power on graphs. We study the expressive power of graph transformers (GTs) by Dwivedi and Bresson (2020) and…

Logic in Computer Science · Computer Science 2026-02-19 Veeti Ahvonen , Maurice Funk , Damian Heiman , Antti Kuusisto , Carsten Lutz

We study succinctness as a measure of the expressive power of transformers. Succinctness -- how compactly a formalism can describe a language relative to other formalisms -- is a classical notion in logic and automata theory. We prove that…

Formal Languages and Automata Theory · Computer Science 2026-05-18 Pascal Bergsträßer , Ryan Cotterell , Anthony W. Lin

We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message…

Machine Learning · Computer Science 2025-06-30 Chaitanya K. Joshi

Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables…

Machine Learning · Computer Science 2026-04-29 Michael C. Mozer , Shoaib Ahmed Siddiqui , Rosanne Liu

We study the expressivity of deep neural networks. Measuring a network's complexity by its number of connections or by its number of neurons, we consider the class of functions for which the error of best approximation with networks of a…

Functional Analysis · Mathematics 2020-07-20 Rémi Gribonval , Gitta Kutyniok , Morten Nielsen , Felix Voigtlaender

Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide domains. However, the understanding to their expressive power remains premature. Focusing on 2-layer…

Machine Learning · Computer Science 2026-05-18 Yuzhu Chen , Tian Qin , Xinmei Tian , Fengxiang He , Dacheng Tao

The usage of transformers has grown from learning about language semantics to forming meaningful visiolinguistic representations. These architectures are often over-parametrized, requiring large amounts of computation. In this work, we…

Computation and Language · Computer Science 2020-07-09 Prajjwal Bhargava

Increasing the size of a Transformer does not always lead to enhanced performance. This phenomenon cannot be explained by the empirical scaling laws. Furthermore, the model's enhanced performance is closely associated with its memorization…

Machine Learning · Computer Science 2024-12-02 Xueyan Niu , Bo Bai , Lei Deng , Wei Han