English
Related papers

Related papers: Fast Reconstruction of Exact Maxwell Dynamics from…

200 papers

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Michele Pratusevich

We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to…

Machine Learning · Computer Science 2021-01-18 Haichao Yu , Haoxiang Li , Honghui Shi , Thomas S. Huang , Gang Hua

Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performance evaluation. Most existing studies that achieve faster evaluation are mostly tied to cell-based…

Machine Learning · Computer Science 2025-10-07 Shiwen Qin , Alexander Auras , Shay B. Cohen , Elliot J. Crowley , Michael Moeller , Linus Ericsson , Jovita Lukasik

Tensors play a vital role in machine learning (ML) and often exhibit properties best explored while maintaining high-order. Efficiently performing ML computations requires taking advantage of sparsity, but generalized hardware support is…

Hardware Architecture · Computer Science 2024-04-26 Gabriel Kulp , Andrew Ensinger , Lizhong Chen

Sampling from a categorical distribution is mathematically simple, but in large-vocabulary decoding, it often triggers extra memory traffic and extra kernels after the LM head. We present FlashSampling, an exact sampling primitive that…

Machine Learning · Computer Science 2026-05-14 Tomas Ruiz , Zhen Qin , Yifan Zhang , Xuyang Shen , Yiran Zhong , Mengdi Wang

For over a decade, explicit memory architectures like the Neural Turing Machine have remained theoretically appealing yet practically intractable for language modeling due to catastrophic gradient instability during Backpropagation Through…

Machine Learning · Computer Science 2026-05-14 Sungwoo Goo , Hwi-yeol Yun , Sangkeun Jung

Compressed Neural Networks have the potential to enable deep learning across new applications and smaller computational environments. However, understanding the range of learning tasks in which such models can succeed is not well studied.…

Machine Learning · Computer Science 2023-08-10 Matt Gorbett , Hossein Shirazi , Indrakshi Ray

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

We derive fundamental lower bounds on the connectivity and the memory requirements of deep neural networks guaranteeing uniform approximation rates for arbitrary function classes in $L^2(\mathbb R^d)$. In other words, we establish a…

Machine Learning · Computer Science 2018-05-17 Helmut Bölcskei , Philipp Grohs , Gitta Kutyniok , Philipp Petersen

Constructing neural networks for function approximation is a classical and longstanding topic in approximation theory. In this paper, we aim at constructing deep neural networks (deep nets for short) with three hidden layers to approximate…

Information Theory · Computer Science 2020-01-14 Xia Liu

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Machine Learning · Computer Science 2026-02-13 Kaicheng Xiao , Haotian Li , Liran Dong , Guoliang Xing

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just the parameter itself, but also its gradient and one or more optimizer state variables.…

Machine Learning · Computer Science 2026-03-13 Jose Javier Gonzalez Ortiz , Abhay Gupta , Christopher Rinard , Davis Blalock

Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs. However, incorporating long histories is resource-intensive. Hence, temporal graph neural networks (TGNNs) often rely on…

Machine Learning · Computer Science 2025-04-11 Or Feldman , Krishna Sri Ipsit Mantri , Carola-Bibiane Schönlieb , Chaim Baskin , Moshe Eliasof

Sparse approximations using highly over-complete dictionaries is a state-of-the-art tool for many imaging applications including denoising, super-resolution, compressive sensing, light-field analysis, and object recognition. Unfortunately,…

Computer Vision and Pattern Recognition · Computer Science 2014-12-03 Ali Ayremlou , Thomas Goldstein , Ashok Veeraraghavan , Richard Baraniuk

The sparse-views x-ray computed tomography (CT) is essential for medical diagnosis and industrial nondestructive testing. However, in particular, the reconstructed image usually suffers from complex artifacts and noise, when the sampling is…

Medical Physics · Physics 2019-10-08 Genwei Ma , Yining Zhu , Xing Zhao

Previous works on meta-learning either relied on elaborately hand-designed network structures or adopted specialized learning rules to a particular domain. We propose a universal framework to optimize the meta-learning process automatically…

Machine Learning · Computer Science 2019-09-10 Xinyue Zheng , Peng Wang , Qigang Wang , Zhongchao shi , Feiyu Xu

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the…

Computation and Language · Computer Science 2017-06-20 Edouard Grave , Armand Joulin , Moustapha Cissé , David Grangier , Hervé Jégou

An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models or the learning of word-embeddings, often posed as…

Neural and Evolutionary Computing · Computer Science 2015-07-15 Pascal Vincent , Alexandre de Brébisson , Xavier Bouthillier

Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to…

Machine Learning · Computer Science 2022-07-13 Selima Curci , Decebal Constantin Mocanu , Mykola Pechenizkiyi