paper-with-me

Papers

Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks

2019-05-27 · Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev, Vitaly Lavrukhin, Ryan Leary, Jason Li, Huyen Nguyen, Yang Zhang, Jonathan M. Cohen

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with momentum and Adam or AdamW. Additionally, NovoGrad (1) is robust to the choice of learning rate and weight initialization, (2) works well in a large batch setting, and (3) has two times smaller memory footprint than Adam.

📄 PDF Abstract BibTeX arXiv:1905.11286

Code (3)

Edresson/VoiceSplit pytorch
NVIDIA/OpenSeq2Seq tf
convergence-lab/novograd pytorch

Tasks

General Classificationimage-classificationLanguage Modelingspeech-recognitionStochastic OptimizationTranslation

Methods 이 논문이 사용한 방법론

AdamW AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling [weight…
SGD with Momentum 설명 없음
Adam 설명 없음
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning

2023-05-23 · Achraf Bahamou, Donald Goldfarb

We propose a new per-layer adaptive step-size procedure for stochastic first-order optimization methods for minimizing empirical loss functions in deep learning, eliminating the need for the user to tune the learning rat…

Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments

2020-01-01 · ICLR 2020 1 · Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev 외

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, m…

General Classificationimage-classificationImage ClassificationLanguage Modeling+5

Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descent

2023-07-21 · Toan N. Nguyen, Phuong Ha Nguyen, Lam M. Nguyen, Marten van Dijk

Each round in Differential Private Stochastic Gradient Descent (DPSGD) transmits a sum of clipped gradients obfuscated with Gaussian noise to a central server which uses this to update a global model which often represen…

Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks

2019-09-25 · Ameya D. Jagtap, Kenji Kawaguchi, George Em. Karniadakis

We propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The…

Data Augmentation

Layer-wise Adaptive Gradient Sparsification for Distributed Deep Learning with Convergence Guarantees

2019-11-20 · Shaohuai Shi, Zhenheng Tang, Qiang Wang, Kaiyong Zhao 외

To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. However, the speedup brought by multiple w…

Distributed OptimizationGPU