Top Papers
PyTorch Distributed: Experiences on Accelerating Data Parallel Training
pytorch/pytorch
•
•
This paper presents the design, implementation, and evaluation of the PyTorch distributed data parallel module.
PyTorch: An Imperative Style, High-Performance Deep Learning Library
pytorch/pytorch
•
•
NeurIPS 2019
Deep learning frameworks have often focused on either usability or speed, but not both.
Automatic Differentiation in PyTorch
pytorch/pytorch
•
•
NIPS 2017 2017
In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models.
Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization
huggingface/pytorch-pretrained-BERT
•
•
In this paper, we address the over-confidence issue and the over-sensitivity issue existing in current RC models simultaneously with the help of external linguistic knowledge.
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
huggingface/pytorch-transformers
•
•
We present a large, tunable neural conversational response generation model, DialoGPT (dialogue generative pre-trained transformer).
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates.
Scikit-learn: Machine Learning in Python
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.