English
Related papers

Related papers: Tropical Attention: Neural Algorithmic Reasoning f…

200 papers

Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation. We present Grid Partitioned Attention (GPA), a new…

Computer Vision and Pattern Recognition · Computer Science 2021-07-09 Nikolay Jetchev , Gökhan Yildirim , Christian Bracher , Roland Vollgraf

Multi-Head Latent Attention (MLA) is a recent attention mechanism adopted in state-of-the-art LLMs such as DeepSeek-v3 and Kimi K2. Thanks to its novel formulation, MLA allows two functionally equivalent but computationally distinct kernel…

Machine Learning · Computer Science 2026-02-13 Ahmet Caner Yüzügüler , Ahmet Çelik , Jiawei Zhuang , Lukas Cavigelli

We develop a tropical analogue of the classical double description method allowing one to compute an internal representation (in terms of vertices) of a polyhedron defined externally (by inequalities). The heart of the tropical algorithm is…

Computational Geometry · Computer Science 2011-12-30 Xavier Allamigeon , Stephane Gaubert , Eric Goubault

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

This paper proposes a tropical geometry-based edge detection framework that reformulates convolution and gradient computations using min-plus and max-plus algebra. The tropical formulation emphasizes dominant intensity variations,…

Algebraic Geometry · Mathematics 2025-05-27 Shivam Kumar Jha S , Jaya NN Iyer

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…

Machine Learning · Computer Science 2021-08-12 Yao Zhang , Yunpu Ma , Thomas Seidl , Volker Tresp

This paper presents a unified mathematical framework for inference in graphical models, building on the observation that graphical models are algebraic varieties. From this geometric viewpoint, observations generated from a model are…

Quantitative Methods · Quantitative Biology 2009-11-10 Lior Pachter , Bernd Sturmfels

Soft attention is a critical mechanism powering LLMs to locate relevant parts within a given context. However, individual attention weights are determined by the similarity of only a single query and key token vector. This "single token…

Computation and Language · Computer Science 2025-07-14 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

The reasoning abilities of Large Language Models (LLMs) can be improved by structurally denoising their weights, yet existing techniques primarily focus on denoising the feed-forward network (FFN) of the transformer block, and can not…

Computation and Language · Computer Science 2025-05-16 Yuxuan Gu , Wuyang Zhou , Giorgos Iacovides , Danilo Mandic

In this paper we use the connections between tropical algebraic geometry and rigid analytic geometry in order to prove two main results. We use tropical methods to prove a theorem about the Newton polygon for convergent power series in…

Algebraic Geometry · Mathematics 2010-07-19 Joseph Rabinoff

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Computation and Language · Computer Science 2025-10-16 Yang Li , Zhichen Dong , Yuhan Sun , Weixun Wang , Shaopan Xiong , Yijia Luo , Jiashun Liu , Han Lu , Jiamang Wang , Wenbo Su , Bo Zheng , Junchi Yan

Tropical mathematics redefines the rules of arithmetic by replacing addition with taking a maximum, and by replacing multiplication with addition. After briefly discussing a tropical version of linear algebra, we study polynomials build…

Algebraic Geometry · Mathematics 2019-08-21 Ralph Morrison

Large language models (LLMs) have significantly improved various aspects of our daily lives. These models have impacted numerous domains, from healthcare to education, enhancing productivity, decision-making processes, and accessibility. As…

Machine Learning · Computer Science 2023-11-01 Zhao Song , Guangyi Xu , Junze Yin

The tropical semiring is an algebraic system with addition ``$\max$'' and multiplication ``$+$''. As well as in conventional algebra, linear programming in the tropical semiring has been developed. In this study, we introduce a new type of…

Optimization and Control · Mathematics 2026-02-03 Yuki Nishida

We present a new, unifying approach following some recent developments on the complexity of neural networks with piecewise linear activations. We treat neural network layers with piecewise linear activations as tropical polynomials, which…

Machine Learning · Statistics 2019-01-31 Vasileios Charisopoulos , Petros Maragos

We introduce a generalized attention mechanism for spherical domains, enabling Transformer architectures to natively process data defined on the two-dimensional sphere - a critical need in fields such as atmospheric physics, cosmology, and…

Machine Learning · Computer Science 2025-05-19 Boris Bonev , Max Rietmann , Andrea Paris , Alberto Carpentieri , Thorsten Kurth

The Attention module finds common usage in language modeling, presenting distinct challenges within the broader scope of Natural Language Processing. Multi-Head Attention (MHA) employs an absolute positional encoding, which imposes…

Computation and Language · Computer Science 2023-08-08 Herman Sugiharto , Aradea , Husni Mubarok

Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- and space-complexity is quadratic in the…

Machine Learning · Computer Science 2022-09-13 Feyza Duman Keles , Pruthuvi Mahesakya Wijewardena , Chinmay Hegde

Scaling pre-trained language models has resulted in large performance gains in various natural language processing tasks but comes with a large cost in memory requirements. Inspired by the position embeddings in transformers, we aim to…

Computation and Language · Computer Science 2023-10-13 Huiyin Xue , Nikolaos Aletras