
BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
Recent works on Binary Neural Networks (BNNs) have made promising progre...
read it

Accelerating Inference for Sparse Extreme MultiLabel Ranking Trees
Treebased models underpin many modern semantic search engines and recom...
read it

PECOS: Prediction for Enormous and Correlated Output Spaces
Many challenging problems in modern applications amount to finding relev...
read it

Towards Lower Bit Multiplication for Convolutional Neural Network Training
Convolutional Neural Networks (CNNs) have been widely used in many field...
read it

Enabling Efficient and Flexible FPGA Virtualization for Deep Learning in the Cloud
FPGAs have shown great potential in providing lowlatency and energyeff...
read it

A Modular Deep Learning Approach for Extreme Multilabel Text Classification
Extreme multilabel classification (XMC) aims to assign to an instance t...
read it

Binary Classification with Karmic, ThresholdQuasiConcave Metrics
Complex performance measures, beyond the popular measure of accuracy, ar...
read it

Nonlinear Inductive Matrix Completion based on Onelayer Neural Networks
The goal of a recommendation system is to predict the interest of a user...
read it

Learning Nonoverlapping Convolutional Neural Networks with Multiple Kernels
In this paper, we consider parameter recovery for nonoverlapping convol...
read it

Recovery Guarantees for Onehiddenlayer Neural Networks
In this paper, we consider regression problems with onehiddenlayer neu...
read it

Online Classification with Complex Metrics
We present a framework and analysis of consistent binary classification ...
read it

Coordinate Descent Methods for Symmetric Nonnegative Matrix Factorization
Given a symmetric nonnegative matrix A, symmetric nonnegative matrix fac...
read it

Proximal QuasiNewton for Computationally Intensive L1regularized Mestimators
We consider the class of optimization problems arising from computationa...
read it
Kai Zhong
is this you? claim profile