
Regularize! Don't Mix: MultiAgent Reinforcement Learning without Explicit Centralized Structures
We propose using regularization for MultiAgent Reinforcement Learning r...
read it

Dual Behavior Regularized Reinforcement Learning
Reinforcement learning has been shown to perform a range of complex task...
read it

Greedy UnMixing for QLearning in MultiAgent Reinforcement Learning
This paper introduces Greedy UnMix (GUM) for cooperative multiagent rei...
read it

dpGAN : Alleviating Mode Collapse in GAN via Diversity Penalty Module
The vanilla GAN [5] suffers from mode collapse deeply, which usually man...
read it

Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss
Graph convolutional networks (GCNs) and their variants have achieved gre...
read it

Resolutioninvariant Person ReID Based on Feature Transformation and Selfweighted Attention
Person Reidentification (ReID) is a critical computer vision task which...
read it

Revealing the Transmission Dynamics of COVID19: A Bayesian Framework for R_t Estimation
In epidemiological modelling, the instantaneous reproduction number, R_t...
read it

Implicit bias of deep linear networks in the large learning rate phase
Correctly choosing a learning rate (scheme) for gradientbased optimizat...
read it

On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization
In recent years, a critical initialization scheme with orthogonal initia...
read it

Gaussian Process Latent Variable Model Factorization for Contextaware Recommender Systems
Contextaware recommender systems (CARS) have gained increasing attentio...
read it

Mean field theory for deep dropout networks: digging up gradient backpropagation deeply
In recent years, the mean field theory has been applied to the study of ...
read it

Magnitude Bounded Matrix Factorisation for Recommender Systems
Low rank matrix factorisation is often used in recommender systems as a ...
read it

Diverse Online Feature Selection
Online feature selection has been an active research area in recent year...
read it

Cooperative Hierarchical Dirichlet Processes: Superposition vs. Maximization
The cooperative hierarchical structure is a common and significant data ...
read it

The Dependent Random Measures with Independent Increments in Mixture Models
When observations are organized into groups where commonalties exist amo...
read it

Smoothed Hierarchical Dirichlet Process: A NonParametric Approach to Constraint Measures
Timevarying mixture densities occur in many scenarios, for example, the...
read it

Bayesian nonparametric image segmentation using a generalized SwendsenWang algorithm
Unsupervised image segmentation aims at clustering the set of pixels of ...
read it

Nonparametric Relational Topic Models through Dependent Gamma Processes
Traditional Relational Topic Models provide a way to discover the hidden...
read it

Infinite Author Topic Model based on Mixed GammaNegative Binomial Process
Incorporating the side information of text corpus, i.e., authors, time s...
read it

An Adaptive Online HDPHMM for Segmentation and Classification of Sequential Data
In the recent years, the desire and need to understand sequential data h...
read it

Learning Hidden Structures with Relational Models by Adequately Involving Rich Information in A Network
Effectively modelling hidden structures in a network is very practical b...
read it

A nonparametric conditional factor regression model for highdimensional input and response
In this paper, we propose a nonparametric conditional factor regression...
read it

Dynamic Infinite MixedMembership Stochastic Blockmodel
Directional and pairwise measurements are often used to model interrela...
read it

Copula MixedMembership Stochastic Blockmodel for IntraSubgroup Correlations
The MixedMembership Stochastic Blockmodel (MMSB) is a popular framework...
read it
Richard Yi Da Xu
is this you? claim profile
Associate Professor and Director of Industry Analytics and Visualisation, and the creator of at Faculty of Engineering & IT's DataLounge initiative.