English
Related papers

Related papers: Compute Better Spent: Replacing Dense Layers with …

200 papers

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT…

High-performance sparse matrix-matrix (SpMM) multiplication is paramount for science and industry, as the ever-increasing sizes of data prohibit using dense data structures. Yet, existing hardware, such as Tensor Cores (TC), is ill-suited…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-22 Patrik Okanovic , Grzegorz Kwasniewski , Paolo Sylos Labini , Maciej Besta , Flavio Vella , Torsten Hoefler

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

We introduce compositional tensor trains (CTTs) for the approximation of multivariate functions, a class of models obtained by composing low-rank functions in the tensor-train format. This format can encode standard approximation tools,…

Numerical Analysis · Mathematics 2025-12-23 Martin Eigel , Charles Miranda , Anthony Nouy , David Sommer

Deep neural networks employ specialized architectures for vision, sequential and language tasks, yet this proliferation obscures their underlying commonalities. We introduce a unified matrix-order framework that casts convolutional,…

Machine Learning · Computer Science 2025-07-24 Yuzhou Zhu

The Recurrent Neural Networks and their variants have shown promising performances in sequence modeling tasks such as Natural Language Processing. These models, however, turn out to be impractical and difficult to train when exposed to very…

Computer Vision and Pattern Recognition · Computer Science 2017-07-07 Yinchong Yang , Denis Krompass , Volker Tresp

Graph neural networks (GNNs) are powerful models that have been successful in various graph representation learning tasks. Whereas gradient boosted decision trees (GBDT) often outperform other machine learning methods when faced with…

Machine Learning · Computer Science 2021-04-01 Sergei Ivanov , Liudmila Prokhorenkova

Recent work on deep learning for tabular data demonstrates the strong performance of deep tabular models, often bridging the gap between gradient boosted decision trees and neural networks. Accuracy aside, a major advantage of neural models…

Shifted-and-Duplicated-Kernel (SDK) mapping has emerged as an effective strategy to accelerate convolutional layers on compute-in-memory (CIM) hardware. However, existing SDK variants (e.g., VWC-SDK) merely optimize mapping for a single CIM…

Hardware Architecture · Computer Science 2026-04-29 Ke Dong , Kejie Huang , Tao Luo , Bo Wang

Artificial intelligence workloads, especially transformer models, exhibit emergent sparsity in which computations perform selective sparse access to dense data. The workloads are inefficient on hardware designed for dense computations and…

Data Structures and Algorithms · Computer Science 2024-02-23 Brian Wheatman , Meghana Madhyastha , Randal Burns

We introduce a learning-based framework to optimize tensor programs for deep learning workloads. Efficient implementations of tensor operators, such as matrix multiplication and high dimensional convolution, are key enablers of effective…

Machine Learning · Computer Science 2019-01-10 Tianqi Chen , Lianmin Zheng , Eddie Yan , Ziheng Jiang , Thierry Moreau , Luis Ceze , Carlos Guestrin , Arvind Krishnamurthy

Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Catalin Ionescu , Orestis Vantzos , Cristian Sminchisescu

With the increased availability of 3D scanning technology, point clouds are moving into the focus of computer vision as a rich representation of everyday scenes. However, they are hard to handle for machine learning algorithms due to their…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Sergey Prokudin , Christoph Lassner , Javier Romero

We show that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance. We focus on the representative case of learning random patterns with binary…

Disordered Systems and Neural Networks · Physics 2015-09-21 Carlo Baldassi , Alessandro Ingrosso , Carlo Lucibello , Luca Saglietti , Riccardo Zecchina

Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best…

Machine Learning · Computer Science 2018-01-29 Jayanta K Dutta , Jiayi Liu , Unmesh Kurup , Mohak Shah

Deep Neural Networks (DNNs) have been proven to be exceptionally effective and have been applied across diverse domains within deep learning. However, as DNN models increase in complexity, the demand for reduced computational costs and…

Neural and Evolutionary Computing · Computer Science 2025-06-12 Xiaotian Chen , Hongyun Liu , Seyed Sahand Mohammadi Ziabari

Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Vasiliy Alekseev , Ilya Lukashevich , Ilia Zharikov , Ilya Vasiliev

Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required…

Machine Learning · Computer Science 2015-12-22 Alexander Novikov , Dmitry Podoprikhin , Anton Osokin , Dmitry Vetrov

With the recent developments in the field of Natural Language Processing, there has been a rise in the use of different architectures for Neural Machine Translation. Transformer architectures are used to achieve state-of-the-art accuracy,…

Computation and Language · Computer Science 2021-11-30 Aditya Mandke , Onkar Litake , Dipali Kadam

We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We consider matrices as…

Machine Learning · Computer Science 2018-02-06 Kien Do , Truyen Tran , Svetha Venkatesh