
Exponential Family Estimation via Adversarial Dynamics Embedding
We present an efficient algorithm for maximum likelihood estimation (MLE...
read it

CostEffective Incentive Allocation via Structured Counterfactual Inference
We address a practical problem ubiquitous in modern industry, in which a...
read it

Retrosynthesis Prediction with Conditional Graph Logic Network
Retrosynthesis is one of the fundamental problems in organic chemistry. ...
read it

Kernel Exponential Family Estimation via Doubly Dual Embedding
We investigate penalized maximum loglikelihood estimation for exponenti...
read it

Neural Networkbased Graph Embedding for CrossPlatform Binary Code Similarity Detection
The problem of crossplatform binary code similarity detection aims at d...
read it

Deep Hyperspherical Learning
Convolution as inner product has been the founding basis of convolutiona...
read it

Towards Blackbox Iterative Machine Teaching
In this paper, we make an important step towards the blackbox machine t...
read it

Iterative Machine Teaching
In this paper, we consider the problem of machine teaching, the inverse ...
read it

Wasserstein Learning of Deep Generative Point Process Models
Point processes are becoming very popular in modeling asynchronous seque...
read it

Learning Combinatorial Optimization Algorithms over Graphs
The design of good heuristics or approximation algorithms for NPhard co...
read it

Deep SemiRandom Features for Nonlinear Function Approximation
We propose semirandom features for nonlinear function approximation. Th...
read it

Diverse Neural Network Learns True Target Functions
Neural networks are a powerful class of functions that can be trained wi...
read it

Distilling Information Reliability and Source Trustworthiness from Digital Traces
Online knowledge repositories typically rely on their users or dedicated...
read it

DataDriven Threshold Machine: Scan Statistics, ChangePoint Detection, and Extreme Bandits
We present a novel distributionfree approach, the datadriven threshold...
read it

Fast and Simple Optimization for Poisson Likelihood Models
Poisson likelihood models have been prevalently used in imaging, social ...
read it

Learning from Conditional Distributions via Dual Embeddings
Many machine learning tasks, such as learning with invariance and policy...
read it

Stochastic Generative Hashing
Learningbased binary hashing has become a powerful paradigm for fast se...
read it

Smart broadcasting: Do you want to be seen?
Many users in online social networks are constantly trying to gain atten...
read it

Detecting weak changes in dynamic events over networks
Large volume of networked streaming event data are becoming increasingly...
read it

Online Supervised Subspace Tracking
We present a framework for supervised subspace tracking, when there are ...
read it

COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Coevolution
Information diffusion in online social networks is affected by the under...
read it

Scan BStatistic for Kernel ChangePoint Detection
Detecting the emergence of an abrupt changepoint is a classic problem i...
read it

Provable Bayesian Inference via Particle Mirror Descent
Bayesian methods are appealing in their flexibility in modeling complex ...
read it

Deep Fried Convnets
The fully connected layers of a deep convolutional neural network typica...
read it

A la Carte  Learning Fast Kernels
Kernel methods have great promise for learning rich statistical represen...
read it

Scalable Kernel Methods via Doubly Stochastic Gradients
The general perception is that kernel methods are not scalable, and neur...
read it

Estimating Diffusion Network Structures: Recovery Conditions, Sample Complexity & Softthresholding Algorithm
Information spreads across social and technological networks, but often ...
read it

Nonparametric Latent Tree Graphical Models: Inference, Estimation, and Structure Learning
Tree structured graphical models are powerful at expressing long range o...
read it

Budgeted Influence Maximization for Multiple Products
The typical algorithmic problem in viral marketing aims to identify a se...
read it

Nonparametric Estimation of MultiView Latent Variable Models
Spectral methods have greatly advanced the estimation of latent variable...
read it

Least Squares Revisited: Scalable Approaches for Multiclass Prediction
This work provides simple algorithms for multiclass (and multilabel) p...
read it

A Spectral Algorithm for Latent Junction Trees
Latent variable models are an elegant framework for capturing rich proba...
read it

Unfolding Latent Tree Structures using 4th Order Tensors
Discovering the latent structure from many observed variables is an impo...
read it

Spectral Methods for Learning Multivariate Latent Tree Structure
This work considers the problem of learning the structure of multivariat...
read it

Infinite Hierarchical MMSB Model for Nested Communities/Groups in Social Networks
Actors in realistic social networks play not one but a number of diverse...
read it

Kernel Bayes' rule
A nonparametric kernelbased method for realizing Bayes' rule is propose...
read it

Variational Reasoning for Question Answering with Knowledge Graph
Knowledge graph (KG) is known to be helpful for the task of question ans...
read it

KnowEvolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
The availability of large scale event data with time stamps has given ri...
read it

On the Complexity of Learning Neural Networks
The stunning empirical successes of neural networks currently lack rigor...
read it

Smoothed Dual Embedding Control
We revisit the Bellman optimality equation with Nesterov's smoothing tec...
read it

Boosting the Actor with Dual Critic
This paper proposes a new actorcriticstyle algorithm called Dual Actor...
read it

GeniePath: Graph Neural Networks with Adaptive Receptive Paths
We present, GeniePath, a scalable approach for learning adaptive recepti...
read it

Learning to Explain: An InformationTheoretic Perspective on Model Interpretation
We introduce instancewise feature selection as a methodology for model i...
read it

SyntaxDirected Variational Autoencoder for Structured Data
Deep generative models have been enjoying success in modeling continuous...
read it

Iterative Learning with Openset Noisy Labels
Largescale datasets possessing clean label annotations are crucial for ...
read it

Decoupled Networks
Inner productbased convolution has been a central component of convolut...
read it

Learning to Optimize via Wasserstein Deep Inverse Optimal Control
We study the inverse optimal control problem in social sciences: we aim ...
read it

Learning towards Minimum Hyperspherical Energy
Neural networks are a powerful class of nonlinear functions that can be ...
read it

KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question ...
read it

Adversarial Attack on Graph Structured Data
Deep learning on graph structures has shown exciting results in various ...
read it
Le Song
is this you? claim profile
Associate Director, Center for Machine Learning, Associate Professor at Georgia Institute of Technology