English
Related papers

Related papers: Stabilizing RNN Gradients through Pre-training

200 papers

Stochastic gradient descent is one of the most successful approaches for solving large-scale problems, especially in machine learning and statistics. At each iteration, it employs an unbiased estimator of the full gradient computed from one…

Numerical Analysis · Mathematics 2018-12-05 Bangti Jin , Xiliang Lu

Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical…

Machine Learning · Computer Science 2026-04-14 Eric Gan

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

By replacing standard non-linearities with polynomial activations, Polynomial Neural Networks (PNNs) are pivotal for applications such as privacy-preserving inference via Homomorphic Encryption (HE). However, training PNNs effectively…

Machine Learning · Computer Science 2025-05-20 Forsad Al Hossain , Tauhidur Rahman

Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders for sequences, which allows to maximize the short-term memory…

Machine Learning · Computer Science 2020-11-06 Antonio Carta , Alessandro Sperduti , Davide Bacciu

Graph Neural Networks (GNNs) have demonstrated remarkable performance across a spectrum of graph-related tasks, however concerns persist regarding their vulnerability to adversarial perturbations. While prevailing defense strategies focus…

Machine Learning · Computer Science 2025-10-28 Sofiane Ennadir , Johannes F. Lutzeyer , Michalis Vazirgiannis , El Houcine Bergou

Stochastic gradient descent (SGD) is a premium optimization method for training neural networks, especially for learning objectively defined labels such as image objects and events. When a neural network is instead faced with subjectively…

Neural and Evolutionary Computing · Computer Science 2022-04-15 Kosmas Pinitas , Konstantinos Makantasis , Antonios Liapis , Georgios N. Yannakakis

In this paper, we study the implicit regularization of stochastic gradient descent (SGD) through the lens of {\em dynamical stability} (Wu et al., 2018). We start by revising existing stability analyses of SGD, showing how the Frobenius…

Machine Learning · Statistics 2023-06-02 Lei Wu , Weijie J. Su

Stochastic Gradient Descent (SGD) has proven to be remarkably effective in optimizing deep neural networks that employ ever-larger numbers of parameters. Yet, improving the efficiency of large-scale optimization remains a vital and highly…

Machine Learning · Computer Science 2020-11-11 Frithjof Gressmann , Zach Eaton-Rosen , Carlo Luschi

The exploding and vanishing gradient problem has been the major conceptual principle behind most architecture and training improvements in recurrent neural networks (RNNs) during the last decade. In this paper, we argue that this principle,…

Machine Learning · Computer Science 2020-03-06 Antônio H. Ribeiro , Koen Tiels , Luis A. Aguirre , Thomas B. Schön

Many efforts have been devoted to training generative latent variable models with autoregressive decoders, such as recurrent neural networks (RNN). Stochastic recurrent models have been successful in capturing the variability observed in…

Machine Learning · Statistics 2017-11-17 Anirudh Goyal , Alessandro Sordoni , Marc-Alexandre Côté , Nan Rosemary Ke , Yoshua Bengio

Deep neural networks, which employ batch normalization and ReLU-like activation functions, suffer from instability in the early stages of training due to the high gradient induced by temporal gradient explosion. In this study, we analyze…

Machine Learning · Computer Science 2023-05-23 Inyoung Paik , Jaesik Choi

Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This…

Machine Learning · Statistics 2018-02-28 Huishuai Zhang , Wei Chen , Tie-Yan Liu

Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they…

Machine Learning · Computer Science 2025-12-09 Shrihari Sridharan , Deepak Ravikumar , Anand Raghunathan , Kaushik Roy

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Recurrent neural networks (RNNs) are widely used throughout neuroscience as models of local neural activity. Many properties of single RNNs are well characterized theoretically, but experimental neuroscience has moved in the direction of…

Machine Learning · Computer Science 2023-01-31 Leo Kozachkov , Michaela Ennis , Jean-Jacques Slotine

Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation…

Machine Learning · Computer Science 2021-07-07 Sungyoon Lee , Hoki Kim , Jaewook Lee

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

Large-scale recurrent networks have drawn increasing attention recently because of their capabilities in modeling a large variety of real-world phenomena and physical mechanisms. This paper studies how to identify all authentic connections…

Machine Learning · Statistics 2015-06-23 Yiyuan She , Yuejia He , Dapeng Wu

Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping with respect to its inputs for sensitivity analysis, or to…

Machine Learning · Computer Science 2019-07-09 Guang-He Lee , David Alvarez-Melis , Tommi S. Jaakkola
‹ Prev 1 8 9 10 Next ›