English
Related papers

Related papers: What's Hidden in a One-layer Randomly Weighted Tra…

200 papers

This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the…

Machine Learning · Computer Science 2016-12-02 David Ha , Andrew Dai , Quoc V. Le

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and…

Computation and Language · Computer Science 2019-10-29 Shrey Desai , Hongyuan Zhan , Ahmed Aly

Recently, Frankle & Carbin (2019) demonstrated that randomly-initialized dense networks contain subnetworks that once found can be trained to reach test accuracy comparable to the trained dense network. However, finding these high…

Machine Learning · Computer Science 2021-03-18 James Diffenderfer , Bhavya Kailkhura

In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match the performance of their dense counterparts. However, most existing approaches…

Artificial Intelligence · Computer Science 2026-01-30 Grzegorz Stefanski , Alberto Presta , Michal Byra

Transformers have achieved great success in recent years. Interestingly, transformers have shown particularly strong in-context learning capability -- even without fine-tuning, they are still able to solve unseen tasks well purely based on…

Machine Learning · Computer Science 2024-11-19 Zihao Li , Yuan Cao , Cheng Gao , Yihan He , Han Liu , Jason M. Klusowski , Jianqing Fan , Mengdi Wang

Discovering a high-performing sparse network within a massive neural network is advantageous for deploying them on devices with limited storage, such as mobile phones. Additionally, model explainability is essential to fostering trust in…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Shantanu Ghosh , Kayhan Batmanghelich

Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstrated that SLTs could also be found within a randomly pruned…

The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information. Motivated by these capabilities, Sanford et al. proposed the sparse token…

Machine Learning · Statistics 2024-06-12 Zixuan Wang , Stanley Wei , Daniel Hsu , Jason D. Lee

This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce…

Machine Learning · Computer Science 2020-07-30 James O' Neill , Greg Ver Steeg , Aram Galstyan

The recently proposed Lottery Ticket Hypothesis of Frankle and Carbin (2019) suggests that the performance of over-parameterized deep networks is due to the random initialization seeding the network with a small fraction of favorable…

Machine Learning · Computer Science 2019-12-18 Rahul Mehta

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and the utility of its…

Computation and Language · Computer Science 2024-06-21 Alexander Yom Din , Taelin Karidi , Leshem Choshen , Mor Geva

Quantization of neural networks has become common practice, driven by the need for efficient implementations of deep neural networks on embedded devices. In this paper, we exploit an oft-overlooked degree of freedom in most networks - for a…

Machine Learning · Computer Science 2019-02-07 Eldad Meller , Alexander Finkelstein , Uri Almog , Mark Grobman

Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual…

Machine Learning · Computer Science 2023-03-28 Haeyong Kang , Jaehong Yoon , Sultan Rizky Madjid , Sung Ju Hwang , Chang D. Yoo

The parameter space for any fixed architecture of feedforward ReLU neural networks serves as a proxy during training for the associated class of functions - but how faithful is this representation? It is known that many different parameter…

Machine Learning · Computer Science 2023-06-13 J. Elisenda Grigsby , Kathryn Lindsey , David Rolnick

We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the…

Machine Learning · Computer Science 2019-01-11 Xu Shell Hu , Sergey Zagoruyko , Nikos Komodakis

A convolutional layer in a Convolutional Neural Network (CNN) consists of many filters which apply convolution operation to the input, capture some special patterns and pass the result to the next layer. If the same patterns also occur at…

Computer Vision and Pattern Recognition · Computer Science 2019-02-04 Okan Köpüklü , Maryam Babaee , Stefan Hörmann , Gerhard Rigoll

Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal…

Machine Learning · Computer Science 2019-04-04 Charles K. Chui , Shao-Bo Lin , Ding-Xuan Zhou

Pruning is a standard technique for reducing the computational cost of deep networks. Many advances in pruning leverage concepts from the Lottery Ticket Hypothesis (LTH). LTH reveals that inside a trained dense network exists sparse…

Machine Learning · Computer Science 2024-03-20 Artur Jordao , George Correa de Araujo , Helena de Almeida Maia , Helio Pedrini