English
Related papers

Related papers: Stabilizing RNN Gradients through Pre-training

200 papers

Despite the enormous success of Graph Convolutional Networks (GCNs) in modeling graph-structured data, most of the current GCNs are shallow due to the notoriously challenging problems of over-smoothening and information squashing along with…

Machine Learning · Computer Science 2022-10-18 Ajay Jaiswal , Peihao Wang , Tianlong Chen , Justin F. Rousseau , Ying Ding , Zhangyang Wang

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

We present PredRNN++, an improved recurrent network for video predictive learning. In pursuit of a greater spatiotemporal modeling capability, our approach increases the transition depth between adjacent states by leveraging a novel…

Machine Learning · Computer Science 2018-11-20 Yunbo Wang , Zhifeng Gao , Mingsheng Long , Jianmin Wang , Philip S. Yu

We give a simple local Polyak-Lojasiewicz (PL) criterion that guarantees linear (exponential) convergence of gradient flow and gradient descent to a zero-loss solution of a nonnegative objective. We then verify this criterion for the…

Machine Learning · Computer Science 2026-02-23 Sourav Chatterjee

Training sparse networks to converge to the same performance as dense neural architectures has proven to be elusive. Recent work suggests that initialization is the key. However, while this direction of research has had some success,…

Machine Learning · Computer Science 2021-06-17 Kale-ab Tessera , Sara Hooker , Benjamin Rosman

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbations and ignore…

Machine Learning · Computer Science 2020-10-07 Pengfei Xia , Bin Li

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

The study of Deep Network (DN) training dynamics has largely focused on the evolution of the loss function, evaluated on or around train and test set data points. In fact, many DN phenomenon were first introduced in literature with that…

Machine Learning · Computer Science 2023-10-23 Ahmed Imtiaz Humayun , Randall Balestriero , Richard Baraniuk

Relieving the reliance of neural network training on a global back-propagation (BP) has emerged as a notable research topic due to the biological implausibility and huge memory consumption caused by BP. Among the existing solutions, local…

Machine Learning · Computer Science 2024-06-11 Yibo Yang , Xiaojie Li , Motasem Alfarra , Hasan Hammoud , Adel Bibi , Philip Torr , Bernard Ghanem

Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges…

Machine Learning · Computer Science 2023-12-27 Yihang Yao , Zuxin Liu , Zhepeng Cen , Peide Huang , Tingnan Zhang , Wenhao Yu , Ding Zhao

For a given stable recurrent neural network (RNN) that is trained to perform a classification task using sequential inputs, we quantify explicit robustness bounds as a function of trainable weight matrices. The sequential inputs can be…

Machine Learning · Computer Science 2022-03-11 Guangyi Liu , Arash Amini , Martin Takac , Nader Motee

Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss…

Machine Learning · Computer Science 2025-11-18 Lawrence Wang , Stephen J. Roberts

The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space -- for example protein folding or evolution. Our study uses a…

Machine Learning · Computer Science 2023-06-07 Shishir Adhikari , Alkan Kabakçıoğlu , Alexander Strang , Deniz Yuret , Michael Hinczewski

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics. Whereas prior work has focused on how different learning…

Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to…

Neural and Evolutionary Computing · Computer Science 2025-09-10 Luigi Troiano , Francesco Gissi , Vincenzo Benedetto , Genny Tortora

Stacking, a heuristic technique for training deep residual networks by progressively increasing the number of layers and initializing new layers by copying parameters from older layers, has proven quite successful in improving the…

Machine Learning · Computer Science 2025-02-20 Naman Agarwal , Pranjal Awasthi , Satyen Kale , Eric Zhao

Despite the recent success of Graph Neural Networks (GNNs), training GNNs on large graphs remains challenging. The limited resource capacities of the existing servers, the dependency between nodes in a graph, and the privacy concern due to…

Machine Learning · Computer Science 2022-03-15 Morteza Ramezani , Weilin Cong , Mehrdad Mahdavi , Mahmut T. Kandemir , Anand Sivasubramaniam

Recent studies have shown that high disparities in effective learning rates (ELRs) across layers in deep neural networks can negatively affect trainability. We formalize how these disparities evolve over time by modeling weight dynamics…

Machine Learning · Computer Science 2024-05-27 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying…

Machine Learning · Computer Science 2013-02-19 Razvan Pascanu , Tomas Mikolov , Yoshua Bengio

Training instability remains a critical challenge in large language model (LLM) pretraining, often manifesting as sudden gradient explosions that waste significant computational resources. We study training failures in a 5M-parameter…

Machine Learning · Computer Science 2026-02-03 Lianhai Ren , Yucheng Ding , Xiao Liu , Qianxiao Li , Peng Cheng , Yeyun Gong