Papers
Browse academic papers referenced in production code
TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms --...
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential solution t...
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introd...
Rainbow: Combining Improvements in Deep Reinforcement Learning
The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN...
RLlib: Abstractions for Distributed Reinforcement Learning
Reinforcement learning (RL) algorithms involve the deep nesting of highly irregular computation patterns, each of which typically exhibits opportunities for distributed computation. We argue for distributing RL components in a composable way by adapt...
A Comparative Analysis of Community Detection Algorithms on Artificial Networks
Many community detection algorithms have been developed to uncover the mesoscopic properties of complex networks. However how good an algorithm is, in terms of accuracy and computing time, remains still open. Testing algorithms on real-world network ...
On Multiplicative Integration with Recurrent Neural Networks
We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from difference sources flows and is integrated in the computational build...
Neural Machine Translation by Jointly Learning to Align and Translate
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize t...
On Using Very Large Target Vocabulary for Neural Machine Translation
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite its recent ...
Calibration of Machine Learning Models
The evaluation of machine learning models is a crucial step before their application because it is essential to assess how well a model will behave for every single case. In many real applications, not only is it important to know the “total” or the ...
Macros that Work Together
Abstract Racket is a large language that is built mostly within itself. Unlike the usual approach taken by non-Lisp languages, the self-hosting of Racket is not a matter of bootstrapping one implementation through a previous implementation, but inste...
Algorithms for geodesics
Algorithms for the computation of geodesics on an ellipsoid of revolution are given. These provide accurate, robust, and fast solutions to the direct and inverse geodesic problems and they allow differential and integral properties of geodesics to be...
On classification, ranking, and probability estimation.
The aim of this thesis was the study of respiration in ocean margin \nsediments and the assessments of tools needed for this purpose.\n \n \nThe first study was on the biological pump and global respiration \npatterns in the deep ocean using an empir...
On the “degrees of freedom” of the lasso
We study the effective degrees of freedom of the lasso in the framework of Stein’s unbiased risk estimation (SURE). We show that the number of nonzero coefficients is an unbiased estimate for the degrees of freedom of the lasso—a conclusion that requ...
Random Features for Large-Scale Kernel Machines
In this paper, we contributed a stereo face recognition formulation which combines appearance and disparity/depth at feature level. We showed that the present-day passive stereovision in combination with 2D appearance images can match up to other met...
The relationship between Precision-Recall and ROC curves.
Receiver Operator Characteristic (ROC) curves are commonly used to present results for binary decision problems in machine learning. However, when dealing with highly skewed datasets, Precision-Recall (PR) curves give a more informative picture of an...