English
Related papers

Related papers: Scaling Recurrent Neural Networks to a Billion Par…

200 papers

We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces…

Machine Learning · Computer Science 2020-05-13 Rohun Tripathi , Bharat Singh

Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to…

Machine Learning · Computer Science 2018-06-14 Trieu H. Trinh , Andrew M. Dai , Minh-Thang Luong , Quoc V. Le

Large language models (LLMs) excel across various tasks, but standard first-order (FO) fine-tuning demands considerable memory, significantly limiting real-world deployment. Recently, zeroth-order (ZO) optimization stood out as a promising…

Machine Learning · Computer Science 2025-11-04 Qitao Tan , Jun Liu , Zheng Zhan , Caiwei Ding , Yanzhi Wang , Xiaolong Ma , Jaewoo Lee , Jin Lu , Geng Yuan

Recurrent neural networks (RNNs) are powerful tools for sequential modeling, but typically require significant overparameterization and regularization to achieve optimal performance. This leads to difficulties in the deployment of large…

Machine Learning · Computer Science 2021-11-11 Charles C. Onu , Jacob E. Miller , Doina Precup

Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Xingyu Wang , Tao Wang

Fine-tuning language models (LMs) has demonstrated success in a wide array of downstream tasks. However, as LMs are scaled up, the memory requirements for backpropagation become prohibitively high. Zeroth-order (ZO) optimization methods can…

Machine Learning · Computer Science 2024-04-15 Tanmay Gautam , Youngsuk Park , Hao Zhou , Parameswaran Raman , Wooseok Ha

To understand the fundamental trade-offs between training stability, temporal dynamics and architectural complexity of recurrent neural networks~(RNNs), we directly analyze RNN architectures using numerical methods of ordinary differential…

Machine Learning · Computer Science 2019-05-01 Murphy Yuezhen Niu , Lior Horesh , Isaac Chuang

Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated…

Machine Learning · Computer Science 2024-05-09 Pengyu Zhang , Yingjie Liu , Yingbo Zhou , Xiao Du , Xian Wei , Ting Wang , Mingsong Chen

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…

Machine Learning · Computer Science 2023-12-18 Xi Chen , Chang Gao , Zuowen Wang , Longbiao Cheng , Sheng Zhou , Shih-Chii Liu , Tobi Delbruck

Zeroth-Order Optimization (ZOO) provides powerful tools for optimizing functions where explicit gradients are unavailable or expensive to compute. However, the underlying mechanisms of popular ZOO methods, particularly those employing…

Machine Learning · Computer Science 2025-06-18 Junbin Qiu , Zhengpeng Xie , Xiangda Yan , Yongjie Yang , Yao Shu

In this paper, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all…

Neural and Evolutionary Computing · Computer Science 2016-05-03 Rohollah Soltani , Hui Jiang

Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens. Token pruning alleviates this issue, yet existing approaches face limitations. Attention-based methods rely…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Youngeun Kim , Youjia Zhang , Huiling Liu , Aecheon Jung , Sunwoo Lee , Sungeun Hong

Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that…

Machine Learning · Statistics 2015-10-07 César Laurent , Gabriel Pereyra , Philémon Brakel , Ying Zhang , Yoshua Bengio

Recently introduced distributed zeroth-order optimization (ZOO) algorithms have shown their utility in distributed reinforcement learning (RL). Unfortunately, in the gradient estimation process, almost all of them require random samples…

Systems and Control · Electrical Eng. & Systems 2024-05-06 Gangshan Jing , He Bai , Jemin George , Aranya Chakrabortty , Piyush K. Sharma

Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases,…

Machine Learning · Statistics 2018-06-20 Kyle Helfrich , Devin Willmott , Qiang Ye

We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable,…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Yann Ollivier , Corentin Tallec , Guillaume Charpiat

This paper investigates the gap in representation powers of Recurrent Neural Networks (RNNs) and Transformers in the context of solving algorithmic problems. We focus on understanding whether RNNs, known for their memory efficiency in…

Machine Learning · Computer Science 2024-12-10 Kaiyue Wen , Xingyu Dang , Kaifeng Lyu

Compared to conventional projection-based model-order-reduction, its neural-network acceleration has the advantage that the online simulations are equation-free, meaning that no system of equations needs to be solved iteratively.…

Machine Learning · Computer Science 2021-09-17 S. Vijayaraghavan , L. Wu , L. Noels , S. P. A. Bordas , S. Natarajan , L. A. A. Beex

The recently proposed Unbiased Online Recurrent Optimization algorithm (UORO, arXiv:1702.05043) uses an unbiased approximation of RTRL to achieve fully online gradient-based learning in RNNs. In this work we analyze the variance of the…

Machine Learning · Computer Science 2019-02-08 Tim Cooijmans , James Martens

Many large-scale production networks include thousands types of final products and tens to hundreds thousands types of raw materials and intermediate products. These networks face complicated inventory management decisions, which are often…

Optimization and Control · Mathematics 2022-01-19 Tan Wan , L. Jeff Hong
‹ Prev 1 4 5 6 7 8 10 Next ›