English
Related papers

Related papers: Tropical Attention: Neural Algorithmic Reasoning f…

200 papers

In this work, we introduce a Tropical Axial Attention neural reasoning architecture that replaces vanilla softmax dot-product attention with max-plus operators, inducing a piecewise-linear structure aligned with dynamic programming…

Populations and Evolution · Quantitative Biology 2026-05-15 Chris Teska , Kurt Pasque , Ruriko Yoshida , Baran Hashemi

To quantify the geometric expressivity of transformers, we introduce a tropical geometry framework to characterize their exact spatial partitioning capabilities. By modeling self-attention as a vector-valued tropical rational map, we prove…

Machine Learning · Computer Science 2026-04-17 Ye Su , Yong Liu

We prove that the Transformer self-attention mechanism in the high-confidence regime ($\beta \to \infty$, where $\beta$ is an inverse temperature) operates in the tropical semiring (max-plus algebra). In particular, we show that taking the…

Machine Learning · Computer Science 2026-01-16 Faruk Alpay , Bilge Senturk

In the last few years there has been a growing interest towards methods for statistical inference and learning based on computational geometry and, notably, tropical geometry, that is, the study of algebraic varieties over the min-plus…

Logic in Computer Science · Computer Science 2025-11-21 Davide Barbarossa , Paolo Pistone

We propose an algebraic geometric framework to study the expressivity of linear activation neural networks. A particular quantity of neural networks that has been actively studied is the number of linear regions, which gives a…

Machine Learning · Computer Science 2024-10-10 Paul Lezeau , Thomas Walker , Yueqi Cao , Shiv Bhatia , Anthea Monod

This work tackles the problem of characterizing and understanding the decision boundaries of neural networks with piecewise linear non-linearity activations. We use tropical geometry, a new development in the area of algebraic geometry, to…

Machine Learning · Computer Science 2022-08-24 Motasem Alfarra , Adel Bibi , Hasan Hammoud , Mohamed Gaafar , Bernard Ghanem

We introduce a simple, easy to implement, and computationally efficient tropical convolutional neural network architecture that is robust against adversarial attacks. We exploit the tropical nature of piece-wise linear neural networks by…

Machine Learning · Computer Science 2024-02-02 Kurt Pasque , Christopher Teska , Ruriko Yoshida , Keiji Miura , Jefferson Huang

The development of artificial intelligence systems with advanced reasoning capabilities represents a persistent and long-standing research question. Traditionally, the primary strategy to address this challenge involved the adoption of…

Machine Learning · Computer Science 2024-02-22 Danilo Numeroso

We revisit the Universal Approximation Theorem(UAT) through the lens of the tropical geometry of neural networks and introduce a constructive, geometry-aware initialization for sigmoidal multi-layer perceptrons (MLPs). Tropical geometry…

Machine Learning · Statistics 2025-10-20 Yi-Shan Chu , Yueh-Cheng Kuo

The quadratic computational complexity of MultiHead SelfAttention (MHSA) remains a fundamental bottleneck in scaling Large Language Models (LLMs) for longcontext tasks. While sparse and linearized attention mechanisms attempt to mitigate…

Computation and Language · Computer Science 2025-12-19 Caner Erden

Multiplicative gating is widely used in neural architectures and has recently been applied to attention layers to improve performance and training stability in large language models. Despite the success of gated attention, the mathematical…

Machine Learning · Computer Science 2026-04-17 Satwik Bathula , Anand A. Joshi

Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention…

Attention plays a fundamental role in both natural and artificial intelligence systems. In deep learning, attention-based neural architectures, such as transformer architectures, are widely used to tackle problems in natural language…

Machine Learning · Computer Science 2022-02-18 Pierre Baldi , Roman Vershynin

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

Artificial Intelligence · Computer Science 2026-02-13 Hanno Ackermann , Hong Cai , Mohsen Ghafoorian , Amirhossein Habibian

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…

Tropical geometry has recently found several applications in the analysis of neural networks with piecewise linear activation functions. This paper presents a new look at the problem of tropical polynomial division and its application to…

Machine Learning · Computer Science 2023-06-28 Ioannis Kordonis , Petros Maragos

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure. A few recent approaches have successfully demonstrated the benefits of…

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Computation and Language · Computer Science 2026-04-16 Jusen Du , Jiaxi Hu , Tao Zhang , Weigao Sun , Yu Cheng

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li
‹ Prev 1 2 3 10 Next ›