paper-with-me

홈 › Papers

Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging

2022-09-29 · Jean Kaddour

Training vision or language models on large datasets can take days, if not weeks. We show that averaging the weights of the k latest checkpoints, each collected at the end of an epoch, can speed up the training progression in terms of loss and accuracy by dozens of epochs, corresponding to time savings up to ~68 and ~30 GPU hours when training a ResNet50 on ImageNet and RoBERTa-Base model on WikiText-103, respectively. We also provide the code and model checkpoint trajectory to reproduce the results and facilitate research on reusing historical weights for faster convergence.

📄 PDF Abstract BibTeX arXiv:2209.14981

Code (1)

jeankaddour/lawa 공식 구현 pytorch

Tasks

GPU

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

A Termination Criterion for Probabilistic PointClouds Registration

2020-10-10 · Simone Fontana, Domenico G. Sorrenti

Probabilistic Point Clouds Registration (PPCR) is an algorithm that, in its multi-iteration version, outperformed state of the art algorithms for local point clouds registration. However, its performances have been teste…

LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation

2026-06-17 · Jiaqi Zhang, Ashton Lee, Anthony Wong, John Zou 외 arxiv

Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirement…

Knowledge DistillationSemantic SegmentationObject Recognition

DARTS+: Improved Differentiable Architecture Search with Early Stopping

2019-09-13 · Hanwen Liang, Shifeng Zhang, Jiacheng Sun, Xingqiu He 외

Recently, there has been a growing interest in automating the process of neural architecture design, and the Differentiable Architecture Search (DARTS) method makes the process available within a few GPU days. However, t…

GPU

A multi-objective perspective on jointly tuning hardware and hyperparameters

2021-06-10 · David Salinas, Valerio Perrone, Olivier Cruchant, Cedric Archambeau

In addition to the best model architecture and hyperparameters, a full AutoML solution requires selecting appropriate hardware automatically. This can be framed as a multi-objective optimization problem: there is not a s…

AutoMLTransfer Learning

Processing-in-memory for genomics workloads

2025-05-31 · William Andrew Simon, Leonid Yavits, Konstantina Koliogeorgi, Yann Falevoz 외

Low-cost, high-throughput DNA and RNA sequencing (HTS) data is the main workforce for the life sciences. Genome sequencing is now becoming a part of Predictive, Preventive, Personalized, and Participatory (termed 'P4') m…