
Permutation Invariant Policy Optimization for MeanField MultiAgent Reinforcement Learning: A Principled Approach
Multiagent reinforcement learning (MARL) becomes more challenging in th...
read it

Vehicle Emissions Prediction with PhysicsAware AI Models: Preliminary Results
Given an onboard diagnostics (OBD) dataset and a physicsbased emission...
read it

StatisticallyRobust Clustering Techniques for Mapping Spatial Hotspots: A Survey
Mapping of spatial hotspots, i.e., regions with significantly higher rat...
read it

Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
Numerous empirical evidences have corroborated the importance of noise i...
read it

IFoodCloud: A Platform for Realtime Sentiment Analysis of Public Opinion about Food Safety in China
The Internet contains a wealth of public opinion on food safety, includi...
read it

Regularized Fingerprinting in Detection and Attribution of Climate Change with Weight Matrix Optimizing the Efficiency in Scaling Factor Estimation
The optimal fingerprinting method for detection and attribution of clima...
read it

SpotTune: Leveraging Transient Resources for Costefficient Hyperparameter Tuning in the Public Cloud
Hyperparameter tuning (HPT) is crucial for many machine learning (ML) a...
read it

Efficient and Robust PropensityScoreBased Methods for Population Inference using Epidemiologic Cohorts
Most epidemiologic cohorts are composed of volunteers who do not represe...
read it

The 4Adic Complexity of A Class of Quaternary Cyclotomic Sequences with Period 2p
In cryptography, we hope a sequence over ℤ_m with period N having larger...
read it

It's All Relative: New Regression Paradigm for Microbiome Compositional Data
Microbiome data are complex in nature, involving high dimensionality, co...
read it

Residual Network Based Direct Synthesis of EM Structures: A Study on OnetoOne Transformers
We propose using machine learning models for the direct synthesis of on...
read it

Adjusted Logistic Propensity Weighting Methods for Population Inference using Nonprobability VolunteerBased Epidemiologic Cohorts
Many epidemiologic studies forgo probability sampling and turn to nonpro...
read it

Adversarial Attacks on Reinforcement Learning based Energy Management Systems of Extended Range Electric Delivery Vehicles
Adversarial examples are firstly investigated in the area of computer vi...
read it

A Physics ModelGuided Online Bayesian Framework for Energy Management of Extended Range Electric Delivery Vehicles
Increasing the fuel economy of hybrid electric vehicles (HEVs) and exten...
read it

How to Retrain Recommender System? A Sequential MetaLearning Method
Practical recommender systems need be periodically retrained to refresh ...
read it

GPUAccelerated Compression and Visualization of LargeScale Vessel Trajectories in Maritime IoT Industries
The automatic identification system (AIS), an automatic vesseltracking ...
read it

TEA: Temporal Excitation and Aggregation for Action Recognition
Temporal modeling is key for action recognition in videos. It normally c...
read it

Polar Coded Diversity on Block Fading Channels via Polar Spectrum
Due to the advantage of capacityachieving, polar codes have been extend...
read it

Deep Reinforcement Learning with Smooth Policy
Deep neural networks have been widely adopted in modern reinforcement le...
read it

Pursuing Sources of Heterogeneity in Modeling Clustered Population
Researchers often have to deal with heterogeneous population with mixed ...
read it

AirtoAir Communications Beyond 5G: A Novel 3D CoMP Transmission Scheme
In this paper, a novel 3D cellular model consisting of aerial base stati...
read it

Deep Learningbased Endtoend Diagnosis System for Avascular Necrosis of Femoral Head
As the first diagnostic imaging modality of avascular necrosis of the fe...
read it

Bilinear Graph Neural Network with Node Interactions
Graph Neural Network (GNN) is a powerful model to learn representations ...
read it

Bilinear Graph Neural Network with Neighbor Interactions
Graph Neural Network (GNN) is a powerful model to learn representations ...
read it

LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
Graph Convolution Network (GCN) has become new stateoftheart for coll...
read it

Coordinated MultiPoint Transmission: A PoissonDelaunay Triangulation Based Approach
Coordinated multipoint (CoMP) transmission is a cooperating technique a...
read it

Dynamic list coloring of 1planar graphs
A graph is kplanar if it can be drawn in the plane so that each edge is...
read it

Examining the impact of data quality and completeness of electronic health records on predictions of patients risks of cardiovascular disease
The objective is to assess the extent of variation of data quality and c...
read it

The structure and the list 3dynamic coloring of outer1planar graphs
An outer1planar graph is a graph admitting a drawing in the plane for ...
read it

Towards Understanding the Importance of Noise in Training Neural Networks
Numerous empirical evidence has corroborated that the noise plays a cruc...
read it

Polar Codes: Analysis and Construction Based on Polar Spectrum
Polar codes are the first class of constructive channel codes achieving ...
read it

Equitable vertex arboricity of ddegenerate graphs
A minimization problem in graph theory socalled the equitable treecolo...
read it

Inductive Bias of Gradient Descent based Adversarial Training on Separable Data
Adversarial training is a principled approach for training robust neural...
read it

Similarity GroupingGuided Neural Network Modeling for Maritime Time Series Prediction
Reliable and accurate prediction of time series plays a crucial role in ...
read it

Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Reidentification
Person reidentification (ReID) models usually show a limited performan...
read it

Edge Federation: Towards an Integrated Service Provisioning Model
Edge computing is a promising computing paradigm for pushing the cloud s...
read it

Transductive ZeroShot Learning with Visual Structure Constraint
Zeroshot Learning (ZSL) aims to recognize objects of the unseen classes...
read it

TechKG: A LargeScale Chinese TechnologyOriented Knowledge Graph
Knowledge graph is a kind of valuable knowledge base which would benefit...
read it

Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context
The use of future contextual information is typically shown to be helpfu...
read it

Object detection and tracking benchmark in industry based on improved correlation filter
Realtime object detection and tracking have shown to be the basis of in...
read it

ProjectionFree Algorithms in Statistical Estimation
FrankWolfe algorithm (FW) and its variants have gained a surge of inter...
read it

CommunicationEfficient ProjectionFree Algorithm for Distributed Optimization
Distributed optimization has gained a surge of interest in recent years....
read it

Gated Recurrent Unit Based Acoustic Modeling with Future Context
The use of future contextual information is typically shown to be helpfu...
read it

A Telecom Perspective on the Internet of Drones: From LTEAdvanced to 5G
Drones are driving numerous and evolving use cases, and creating transfo...
read it

Discriminative Learning of Latent Features for ZeroShot Recognition
Zeroshot learning (ZSL) aims to recognize unseen image categories by le...
read it

Mixed Supervised Object Detection with Robust Objectness Transfer
In this paper, we consider the problem of leveraging existing fully labe...
read it

A Framework in CRM Customer Lifecycle: Identify Downward Trend and Potential Issues Detection
Customer retention is one of the primary goals in the area of customer r...
read it

Fast Global Convergence via Landscape of Empirical Loss
While optimizing convex objective (loss) functions has been a powerhouse...
read it

Machine Learning for Survival Analysis: A Survey
Accurately predicting the time of occurrence of an event of interest is ...
read it

Solving MultiObjective MDP with Lexicographic Preference: An application to stochastic planning with multiple quantile objective
In most common settings of Markov Decision Process (MDP), an agent evalu...
read it
Yan Li
is this you? claim profile
Research Investigator in the Department of Computational Medicine and Bioinformatics at University of Michigan