
Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
Prior works on formalizing explanations of a graph neural network (GNN) ...
read it

Data augmentation as stochastic optimization
We present a theoretical framework recasting data augmentation as stocha...
read it

MultiAgent Deep Reinforcement Learning for HVAC Control in Commercial Buildings
In commercial buildings, about 40 is attributed to Heating, Ventilation,...
read it

Likelihood landscape and maximum likelihood estimation for the discrete orbit recovery model
We study the nonconvex optimization landscape for maximum likelihood es...
read it

Multiobjective Ranking via Constrained Optimization
In this paper, we introduce an Augmented Lagrangian based method to inco...
read it

Line as object: datasets and framework for semantic line segment detection
In this work, we propose a learningbased approach to the task of detect...
read it

Testing Robustness Against Unforeseen Adversaries
Considerable work on adversarial defense has studied robustness to a fix...
read it

Learning Fair Classifiers in Online Stochastic Settings
In many real life situations, including job and loan applications, gatek...
read it

Txilm: Lossy Block Compression with Salted Short Hashing
Current blockchains are restricted by the low throughput. Aimed at this ...
read it

Transfer of Adversarial Robustness Between Perturbation Types
We study the transfer of adversarial robustness of deep neural networks ...
read it

Principal components in linear mixed models with general bulk
We study the outlier eigenvalues and eigenvectors in variance components...
read it

An ActivePassive Measurement Study of TCP Performance over LTE on Highspeed Rails
Highspeed rail (HSR) systems potentially provide a more efficient way o...
read it

Learning Vine Copula Models For Synthetic Data Generation
A vine copula model is a flexible highdimensional dependence model whic...
read it

Limited Gradient Descent: Learning With Noisy Labels
Label noise may handicap the generalization of classifiers, and it is an...
read it

Spiked covariances and principal components analysis in highdimensional random effects models
We study principal components analyses in multivariate random and mixed ...
read it

Development of a computeraided design software for dental splint in orthognathic surgery
In the orthognathic surgery, dental splints are important and necessary ...
read it

Sparsifying Neural Network Connections for Face Recognition
This paper proposes to learn highperformance deep ConvNets with sparse ...
read it

From random walks to distances on unweighted graphs
Large unweighted directed graphs are commonly used to capture relations ...
read it

DeepID3: Face Recognition with Very Deep Neural Networks
The stateoftheart of face recognition has been significantly advanced...
read it

Deeply learned face representations are sparse, selective, and robust
This paper designs a highperformance deep convolutional network (DeepID...
read it

Metric recovery from directed unweighted graphs
We analyze directed, unweighted graphs obtained from x_i∈R^d by connecti...
read it

Deep Learning Face Representation by Joint IdentificationVerification
The key challenge of face recognition is to develop effective feature re...
read it

Efficient Natural Evolution Strategies
Efficient Natural Evolution Strategies (eNES) is a novel alternative to ...
read it

On the Size of the Online Kernel Sparsification Dictionary
We analyze the size of the dictionary constructed from online kernel spa...
read it

Natural Evolution Strategies
This paper presents Natural Evolution Strategies (NES), a recent family ...
read it

A Linear Time Natural Evolution Strategy for NonSeparable Functions
We present a novel Natural Evolution Strategy (NES) variant, the RankOn...
read it

Planning to Be Surprised: Optimal Bayesian Exploration in Dynamic Environments
To maximize its success, an AGI typically needs to explore its initially...
read it
Yi Sun
is this you? claim profile