b'Yi Sun'

Data augmentation as stochastic optimization

We present a theoretical framework recasting data augmentation as stocha...
10/21/2020 ∙ by Boris Hanin, et al. ∙ 0 ∙ share

read it
Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings

In commercial buildings, about 40 is attributed to Heating, Ventilation,...
06/25/2020 ∙ by Liang Yu, et al. ∙ 0 ∙ share

read it
Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model

We study the non-convex optimization landscape for maximum likelihood es...
03/31/2020 ∙ by Zhou Fan, et al. ∙ 0 ∙ share

read it
Multi-objective Ranking via Constrained Optimization

In this paper, we introduce an Augmented Lagrangian based method to inco...
02/13/2020 ∙ by Michinari Momma, et al. ∙ 0 ∙ share

read it
Line as object: datasets and framework for semantic line segment detection

In this work, we propose a learning-based approach to the task of detect...
09/14/2019 ∙ by Yi Sun, et al. ∙ 10 ∙ share

read it
Testing Robustness Against Unforeseen Adversaries

Considerable work on adversarial defense has studied robustness to a fix...
08/21/2019 ∙ by Daniel Kang, et al. ∙ 1 ∙ share

read it
Learning Fair Classifiers in Online Stochastic Settings

In many real life situations, including job and loan applications, gatek...
08/19/2019 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
Txilm: Lossy Block Compression with Salted Short Hashing

Current blockchains are restricted by the low throughput. Aimed at this ...
06/15/2019 ∙ by Donghui Ding, et al. ∙ 0 ∙ share

read it
Transfer of Adversarial Robustness Between Perturbation Types

We study the transfer of adversarial robustness of deep neural networks ...
05/03/2019 ∙ by Daniel Kang, et al. ∙ 12 ∙ share

read it
Principal components in linear mixed models with general bulk

We study the outlier eigenvalues and eigenvectors in variance components...
03/22/2019 ∙ by Zhou Fan, et al. ∙ 0 ∙ share

read it
An Active-Passive Measurement Study of TCP Performance over LTE on High-speed Rails

High-speed rail (HSR) systems potentially provide a more efficient way o...
12/12/2018 ∙ by Jing Wang, et al. ∙ 0 ∙ share

read it
Learning Vine Copula Models For Synthetic Data Generation

A vine copula model is a flexible high-dimensional dependence model whic...
12/04/2018 ∙ by Yi Sun, et al. ∙ 6 ∙ share

read it
Limited Gradient Descent: Learning With Noisy Labels

Label noise may handicap the generalization of classifiers, and it is an...
11/20/2018 ∙ by Yi Sun, et al. ∙ 14 ∙ share

read it
Spiked covariances and principal components analysis in high-dimensional random effects models

We study principal components analyses in multivariate random and mixed ...
06/25/2018 ∙ by Zhou Fan, et al. ∙ 0 ∙ share

read it
Development of a computer-aided design software for dental splint in orthognathic surgery

In the orthognathic surgery, dental splints are important and necessary ...
03/09/2017 ∙ by Xiaojun Chen, et al. ∙ 0 ∙ share

read it
Sparsifying Neural Network Connections for Face Recognition

This paper proposes to learn high-performance deep ConvNets with sparse ...
12/07/2015 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
From random walks to distances on unweighted graphs

Large unweighted directed graphs are commonly used to capture relations ...
11/02/2015 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
DeepID3: Face Recognition with Very Deep Neural Networks

The state-of-the-art of face recognition has been significantly advanced...
02/03/2015 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
Deeply learned face representations are sparse, selective, and robust

This paper designs a high-performance deep convolutional network (DeepID...
12/03/2014 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
Metric recovery from directed unweighted graphs

We analyze directed, unweighted graphs obtained from x_i∈R^d by connecti...
11/20/2014 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Deep Learning Face Representation by Joint Identification-Verification

The key challenge of face recognition is to develop effective feature re...
06/18/2014 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
Efficient Natural Evolution Strategies

Efficient Natural Evolution Strategies (eNES) is a novel alternative to ...
09/26/2012 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
On the Size of the Online Kernel Sparsification Dictionary

We analyze the size of the dictionary constructed from online kernel spa...
06/18/2012 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
Natural Evolution Strategies

This paper presents Natural Evolution Strategies (NES), a recent family ...
06/22/2011 ∙ by Daan Wierstra, et al. ∙ 0 ∙ share

read it
A Linear Time Natural Evolution Strategy for Non-Separable Functions

We present a novel Natural Evolution Strategy (NES) variant, the Rank-On...
06/10/2011 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it
Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments

To maximize its success, an AGI typically needs to explore its initially...
03/29/2011 ∙ by Yi Sun, et al. ∙ 0 ∙ share

read it

Yi Sun

Featured Co-authors

Hao Wang

Xiaogang Wang

Tao Jiang

Xiaoou Tang

Jing Wang

Jürgen Schmidhuber

Yihong Wu

Jan Egger

Juergen Schmidhuber

Kai Sun

Tommi S. Jaakkola

Data augmentation as stochastic optimization

Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings

Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model

Multi-objective Ranking via Constrained Optimization

Line as object: datasets and framework for semantic line segment detection

Testing Robustness Against Unforeseen Adversaries

Learning Fair Classifiers in Online Stochastic Settings

Txilm: Lossy Block Compression with Salted Short Hashing

Transfer of Adversarial Robustness Between Perturbation Types

Principal components in linear mixed models with general bulk

An Active-Passive Measurement Study of TCP Performance over LTE on High-speed Rails

Learning Vine Copula Models For Synthetic Data Generation

Limited Gradient Descent: Learning With Noisy Labels

Spiked covariances and principal components analysis in high-dimensional random effects models

Development of a computer-aided design software for dental splint in orthognathic surgery

Sparsifying Neural Network Connections for Face Recognition

From random walks to distances on unweighted graphs

DeepID3: Face Recognition with Very Deep Neural Networks

Deeply learned face representations are sparse, selective, and robust

Metric recovery from directed unweighted graphs

Deep Learning Face Representation by Joint Identification-Verification

Efficient Natural Evolution Strategies

On the Size of the Online Kernel Sparsification Dictionary

Natural Evolution Strategies

A Linear Time Natural Evolution Strategy for Non-Separable Functions

Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments