paper-with-me

Papers

Effective Approaches to Batch Parallelization for Dynamic Neural Network Architectures

2017-07-08 · Joseph Suarez, Clare Zhu

We present a simple dynamic batching approach applicable to a large class of dynamic architectures that consistently yields speedups of over 10x. We provide performance bounds when the architecture is not known a priori and a stronger bound in the special case where the architecture is a predetermined balanced tree. We evaluate our approach on Johnson et al.'s recent visual question answering (VQA) result of his CLEVR dataset by Inferring and Executing Programs (IEP). We also evaluate on sparsely gated mixture of experts layers and achieve speedups of up to 1000x over the naive implementation.

📄 PDF Abstract BibTeX arXiv:1707.02402

Code (1)

jsuarez5341/Efficient-Dynamic-Batching 공식 구현 pytorch

Tasks

Mixture-of-ExpertsQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Seesaw: High-throughput LLM Inference via Model Re-sharding

2025-03-09 · Qidong Su, Wei Zhao, Xin Li, Muralidhar Andoorveedu 외

To improve the efficiency of distributed large language model (LLM) inference, various parallelization strategies, such as tensor and pipeline parallelism, have been proposed. However, the distinct computational characte…

Computational EfficiencyLanguage ModelingLanguage ModellingLarge Language Model+1

GANGR: GAN-Assisted Scalable and Efficient Global Routing Parallelization

2025-11-21 · Hadi Khodaei Jooshin, Inna Partin-Vaisband arxiv

Global routing is a critical stage in electronic design automation (EDA) that enables early estimation and optimization of the routability of modern integrated circuits with respect to congestion, power dissipation, and …

Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration

2026-05-18 · Sachin Garg, Michał Dereziński arxiv

Accelerating stochastic gradient methods with classical momentum schemes, such as Polyak's heavy ball, has proven highly successful in training large-scale machine learning models, particularly when combined with the har…

Minibatch and Parallelization for Online Large Margin Structured Learning

2013-06-01 · NAACL 2013 6 · Kai Zhao, Liang Huang
Dependency ParsingPart-Of-Speech Tagging

The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning

2017-12-18 · ICML 2018 7 · Siyuan Ma, Raef Bassily, Mikhail Belkin

In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained…