
-
RAILS: A Robust Adversarial Immune-inspired Learning System
Adversarial attacks against deep neural networks are continuously evolvi...
read it
-
Cortex: A Compiler for Recursive Deep Learning Models
Optimizing deep learning models is generally performed in two steps: (i)...
read it
-
Dynamic Tensor Rematerialization
Checkpointing enables training deep learning models under restricted mem...
read it
-
Relay: A High-Level Compiler for Deep Learning
Frameworks for writing, compiling, and optimizing deep learning (DL) mod...
read it
-
Relay: A High-Level IR for Deep Learning
Frameworks for writing, compiling, and optimizing deep learning (DL) mod...
read it
-
ADARES: Adaptive Resource Management for Virtual Machines
Virtual execution environments allow for consolidation of multiple appli...
read it
-
Automating Generation of Low Precision Deep Learning Operators
State of the art deep learning models have made steady progress in the f...
read it
-
Relay: A New IR for Machine Learning Frameworks
Machine learning powers diverse services in industry including search, t...
read it
-
VTA: An Open Hardware-Software Stack for Deep Learning
Hardware acceleration is an enabler for ubiquitous and efficient deep le...
read it
-
Learning to Optimize Tensor Programs
We introduce a learning-based framework to optimize tensor programs for ...
read it
-
TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
There is an increasing need to bring machine learning to a wide diversit...
read it
-
TVM: End-to-End Optimization Stack for Deep Learning
Scalable frameworks, such as TensorFlow, MXNet, Caffe, and PyTorch drive...
read it
-
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
MXNet is a multi-language machine learning (ML) library to ease the deve...
read it
-
Net2Net: Accelerating Learning via Knowledge Transfer
We introduce techniques for rapidly transferring the information stored ...
read it
-
A Complete Recipe for Stochastic Gradient MCMC
Many recent Markov chain Monte Carlo (MCMC) samplers leverage continuous...
read it
-
Empirical Evaluation of Rectified Activations in Convolutional Network
In this paper we investigate the performance of different types of recti...
read it
-
A Parallel and Efficient Algorithm for Learning to Match
Many tasks in data mining and related fields can be formalized as matchi...
read it
-
Stochastic Gradient Hamiltonian Monte Carlo
Hamiltonian Monte Carlo (HMC) sampling methods provide a mechanism for d...
read it
-
Feature-Based Matrix Factorization
Recommender system has been more and more popular and widely used in man...
read it