paper-with-me

홈 › Papers

The Effect of Network Width on the Performance of Large-batch Training

2018-06-11 · NeurIPS 2018 12 · Lingjiao Chen, Hongyi Wang, Jinman Zhao, Dimitris Papailiopoulos, Paraschos Koutris

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce these overheads; however, large batches can affect the convergence properties and generalization performance of SGD. In this work, we take a first step towards analyzing how the structure (width and depth) of a neural network affects the performance of large-batch training. We present new theoretical results which suggest that--for a fixed number of parameters--wider networks are more amenable to fast large-batch training compared to deeper ones. We provide extensive experiments on residual and fully-connected neural networks which suggest that wider networks can be trained using larger batches without incurring a convergence slow-down, unlike their deeper variants.

📄 PDF Abstract BibTeX arXiv:1806.03791

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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

The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study

2019-05-09 · Daniel S. Park, Jascha Sohl-Dickstein, Quoc V. Le, Samuel L. Smith

We investigate how the final parameters found by stochastic gradient descent are influenced by over-parameterization. We generate families of models by increasing the number of channels in a base network, and then perfor…

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training

2025-08-19 · Yishun Lu, Wesley Armour arxiv

Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens of thousands of training samples. However, most existing optimizers struggle to perform effect…

Mini-batch Serialization: CNN Training with Inter-layer Data Reuse

2018-09-30 · Sangkug Lym, Armand Behroozi, Wei Wen, Ge Li 외

Training convolutional neural networks (CNNs) requires intense computations and high memory bandwidth. We find that bandwidth today is over-provisioned because most memory accesses in CNN training can be eliminated by re…

Threshold-Based Exclusive Batching for LLM Inference

2026-05-30 · Weifang Zhang, Yuzhou Nie, Bowen Pang, Guangrui Ma 외 arxiv

Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) inference due to its efficiency in maximizing compute and memory utilizat…

Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods

2024-02-05 · Bo-Kyeong Kim, Geonmin Kim, Tae-Ho Kim, Thibault Castells 외

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads…