English
Related papers

Related papers: projUNN: efficient method for training deep networ…

200 papers

Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tuning method that addresses parameter-efficiency by learning prompt embeddings, but these…

Computation and Language · Computer Science 2026-04-14 Zijun Wu , Yongchang Hao , Lili Mou

We investigate online nonlinear regression with continually running recurrent neural network networks (RNNs), i.e., RNN-based online learning. For RNN-based online learning, we introduce an efficient first-order training algorithm that…

Machine Learning · Computer Science 2021-06-01 N. Mert Vural , Selim F. Yilmaz , Fatih Ilhan , Suleyman S. Kozat

The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks. This issue is critical in practical supervised learning settings, such as the ones in…

Machine Learning · Computer Science 2023-06-09 Simone Marullo , Matteo Tiezzi , Marco Gori , Stefano Melacci , Tinne Tuytelaars

Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient vanishing and exploding problems and thus difficult to learn long-term patterns and construct deep networks. To address these problems, this paper…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Shuai Li , Wanqing Li , Chris Cook , Yanbo Gao

A neural network is essentially a high-dimensional complex mapping model by adjusting network weights for feature fitting. However, the spectral bias in network training leads to unbearable training epochs for fitting the high-frequency…

Signal Processing · Electrical Eng. & Systems 2021-06-22 Zhi Zeng , Pengpeng Shi , Fulei Ma , Peihan Qi

Deep neural networks have achieved impressive performance in many applications but their large number of parameters lead to significant computational and storage overheads. Several recent works attempt to mitigate these overheads by…

Machine Learning · Computer Science 2019-06-17 Vikash Sehwag , Shiqi Wang , Prateek Mittal , Suman Jana

Nowadays deep learning is dominating the field of machine learning with state-of-the-art performance in various application areas. Recently, spiking neural networks (SNNs) have been attracting a great deal of attention, notably owning to…

Machine Learning · Computer Science 2019-02-28 Seongsik Park , Sang-gil Lee , Hyunha Nam , Sungroh Yoon

Designing deep neural networks is an art that often involves an expensive search over candidate architectures. To overcome this for recurrent neural nets (RNNs), we establish a connection between the hidden state dynamics in an RNN and…

Machine Learning · Computer Science 2021-12-14 Tan M. Nguyen , Richard G. Baraniuk , Andrea L. Bertozzi , Stanley J. Osher , Bao Wang

This work develops a new method for estimating and optimizing the directed information rate between two jointly stationary and ergodic stochastic processes. Building upon recent advances in machine learning, we propose a recurrent neural…

Information Theory · Computer Science 2022-03-29 Dor Tsur , Ziv Aharoni , Ziv Goldfeld , Haim Permuter

Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore…

Machine Learning · Computer Science 2022-08-18 Hyounguk Shon , Janghyeon Lee , Seung Hwan Kim , Junmo Kim

Backpropagation is still the de facto algorithm used today to train neural networks. With the exponential growth of recent architectures, the computational cost of this algorithm also becomes a burden. The recent PEPITA and forward-only…

Machine Learning · Computer Science 2025-12-25 Paul Caillon , Alex Colagrande , Erwan Fagnou , Blaise Delattre , Alexandre Allauzen

Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding…

Computer Vision and Pattern Recognition · Computer Science 2017-04-11 Di Xie , Jiang Xiong , Shiliang Pu

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as…

Machine Learning · Computer Science 2017-09-25 Liang Zhao , Siyu Liao , Yanzhi Wang , Zhe Li , Jian Tang , Victor Pan , Bo Yuan

Neural networks (NN)-based learning algorithms are strongly affected by the choices of initialization and data distribution. Different optimization strategies have been proposed for improving the learning trajectory and finding a better…

Machine Learning · Computer Science 2021-03-19 Yimeng Min

Deep Neural Networks (DNNs) on hardware is facing excessive computation cost due to the massive number of parameters. A typical training pipeline to mitigate over-parameterization is to pre-define a DNN structure first with redundant…

Neural and Evolutionary Computing · Computer Science 2019-12-19 Xiaocong Du , Zheng Li , Yufei Ma , Yu Cao

The success of deep learning comes at a tremendous computational and energy cost, and the scalability of training massively overparametrized neural networks is becoming a real barrier to the progress of artificial intelligence (AI). Despite…

Machine Learning · Computer Science 2024-02-09 Yichuan Deng , Hang Hu , Zhao Song , Omri Weinstein , Danyang Zhuo

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Computation and Language · Computer Science 2021-06-10 Demi Guo , Alexander M. Rush , Yoon Kim

We investigate deep morphological neural networks (DMNNs). We demonstrate that despite their inherent non-linearity, "linear" activations are essential for DMNNs. To preserve their inherent sparsity, we propose architectures that constraint…

Machine Learning · Computer Science 2025-12-24 Konstantinos Fotopoulos , Petros Maragos

The growth in the complexity of Convolutional Neural Networks (CNNs) is increasing interest in partitioning a network across multiple accelerators during training and pipelining the backpropagation computations over the accelerators.…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-01-01 Lifu Zhang , Tarek S. Abdelrahman

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Machine Learning · Computer Science 2020-05-26 Mohammed Sharafath Abdul Hameed , Gavneet Singh Chadha , Andreas Schwung , Steven X. Ding