English
Related papers

Related papers: How Smoothing is N-simplicial Attention?

200 papers

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

We study the optimization of non-convex functions that are not necessarily smooth (gradient and/or Hessian are Lipschitz) using first order methods. Smoothness is a restrictive assumption in machine learning in both theory and practice,…

Optimization and Control · Mathematics 2025-06-27 Daniel Yiming Cao , August Y. Chen , Karthik Sridharan , Benjamin Tang

There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality and the potential for observational overfitting through…

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Large language models (LLMs) have shown their power in different areas. Attention computation, as an important subroutine of LLMs, has also attracted interests in theory. Recently the static computation and dynamic maintenance of attention…

Data Structures and Algorithms · Computer Science 2023-04-11 Yichuan Deng , Sridhar Mahadevan , Zhao Song

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

Computation and Language · Computer Science 2019-06-05 Matthias Sperber , Graham Neubig , Ngoc-Quan Pham , Alex Waibel

Graph representation learning has rapidly emerged as a pivotal field of study. Despite its growing popularity, the majority of research has been confined to embedding single-layer graphs, which fall short in representing complex systems…

Machine Learning · Computer Science 2024-03-29 Marco Bongiovanni , Luca Gallo , Roberto Grasso , Alfredo Pulvirenti

Modern causal language models stack many attention blocks to improve performance, but not all blocks are necessary for every task. We propose Hopscotch, a simple yet effective method that identifies and skips attention blocks with least…

Computation and Language · Computer Science 2025-09-16 Mustafa Eyceoz , Nikhil Shivakumar Nayak , Hao Wang , Ligong Han , Akash Srivastava

Modern multimodal systems deployed in industrial and safety-critical environments must remain reliable under partial sensor failures, signal degradation, or cross-modal inconsistencies. This work introduces a mathematically grounded…

Machine Learning · Computer Science 2026-03-27 Diyar Altinses , Andreas Schwung

We formalize the problem of machine unlearning as design of efficient unlearning algorithms corresponding to learning algorithms which perform a selection of adaptive queries from structured query classes. We give efficient unlearning…

Machine Learning · Computer Science 2023-07-24 Enayat Ullah , Raman Arora

The ability to model intra-modal and inter-modal interactions is fundamental in multimodal machine learning. The current state-of-the-art models usually adopt deep learning models with fixed structures. They can achieve exceptional…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Qingpei Guo , Kaisheng Yao , Wei Chu

Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models…

Computation and Language · Computer Science 2019-07-09 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention…

Machine Learning · Statistics 2020-10-22 Xinjie Fan , Shujian Zhang , Bo Chen , Mingyuan Zhou

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

Linear attention has emerged as a promising direction for scaling Vision Transformers beyond the quadratic cost of dense self-attention. A prevalent strategy is to compress spatial tokens into a compact set of intermediate proxies that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yuntong Li , Hainuo Wang , Hengxing Liu , Mingjia Li , Xiaojie Guo

Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the attention matrix during the softmax function computation.…

Machine Learning · Computer Science 2025-02-13 Yichuan Deng , Zhao Song , Jing Xiong , Chiwun Yang

In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships. However, current neural network approaches designed for hypergraphs are mostly shallow, thus…

Machine Learning · Computer Science 2022-11-03 Guanzi Chen , Jiying Zhang , Xi Xiao , Yang Li

We present a subgradient method for minimizing non-smooth, non-Lipschitz convex optimization problems. The only structure assumed is that a strictly feasible point is known. We extend the work of Renegar [5] by taking a different…

Optimization and Control · Mathematics 2018-02-28 Benjamin Grimmer

A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs. Mathematically, this means one strives…

Machine Learning · Computer Science 2024-06-04 Bernd Prach , Christoph H. Lampert

Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input objects to class probabilities and do not focus on the ones…

Machine Learning · Computer Science 2023-06-06 Mikhail Pautov , Olesya Kuznetsova , Nurislam Tursynbek , Aleksandr Petiushko , Ivan Oseledets