
Endtoend Robustness for SensingReasoning Machine Learning Pipelines
As machine learning (ML) being applied to many missioncritical scenario...
read it

Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
For recovering 3D object poses from 2D images, a prevalent method is to ...
read it

Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Decentralized Online Learning (online learning in decentralized networks...
read it

Adversarially Trained Model Compression: When Robustness Meets Efficiency
The robustness of deep models to adversarial attacks has gained signific...
read it

Depth Edge Guided CNNs for Sparse Depth Upsampling
Guided sparse depth upsampling aims to upsample an irregularly sampled s...
read it

TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Starcraft II (SCII) is widely considered as the most challenging Real Ti...
read it

An Interactive Control Approach to 3D Shape Reconstruction
The ability to accurately reconstruct the 3D facets of a scene is one of...
read it

Fully Implicit Online Learning
Regularized online learning is widely used in machine learning. In this ...
read it

IMRAM: Iterative Matching with Recurrent Attention Memory for CrossModal ImageText Retrieval
Enabling bidirectional retrieval of images and texts is important for u...
read it

Variance Reduced methods for Nonconvex Composition Optimization
This paper explores the nonconvex composition optimization in the form ...
read it

Dualityfree Methods for Stochastic Composition Optimization
We consider the composition optimization with two expectedvalue functio...
read it

Asynchronous Decentralized Parallel Stochastic Gradient Descent
Recent work shows that decentralized parallel stochastic gradient decent...
read it

Cascaded Regionbased Densely Connected Network for Event Detection: A Seismic Application
Automatic event detection from time series signals has wide applications...
read it

Lifelong Metric Learning
The stateoftheart online learning approaches are only capable of lear...
read it

An Interactive Greedy Approach to Group Sparsity in High Dimension
Sparsity learning with known grouping structures has received considerab...
read it

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
Most distributed machine learning systems nowadays, including TensorFlow...
read it

Asynchronous Parallel Empirical Variance Guided Algorithms for the Thresholding Bandit Problem
This paper considers the multiarmed thresholding bandit problem  iden...
read it

On The Projection Operator to A Threeview Cardinality Constrained Set
The cardinality constraint is an intrinsic way to restrict the solution ...
read it

GaDei: On Scaleup Training As A Service For Deep Learning
Deep learning (DL) trainingasaservice (TaaS) is an important emerging...
read it

The ZipML Framework for Training Models with EndtoEnd Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
Recently there has been significant interest in training machinelearnin...
read it

Accelerating Stochastic Composition Optimization
Consider the stochastic composition optimization problem where the objec...
read it

Efficient Estimation of Compressible StateSpace Models with Application to Calcium Signal Deconvolution
In this paper, we consider linear statespace models with compressible i...
read it

Exclusive Sparsity Norm Minimization with Random Groups via Cone Projection
Many practical applications such as gene expression analysis, multitask...
read it

Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization
Asynchronous parallel implementations of stochastic gradient (SG) have b...
read it

ForwardBackward Greedy Algorithms for General Convex Smooth Functions over A Cardinality Constraint
We consider forwardbackward greedy algorithms for solving sparse featur...
read it

Dictionary LASSO: Guaranteed Sparse Recovery under Linear Transformation
We consider the following signal recovery problem: given a measurement m...
read it

Robust Dequantized Compressive Sensing
We consider the reconstruction problem in compressed sensing in which th...
read it

A GameTheoretic Method for MultiPeriod Demand Response: Revenue Maximization, Power Allocation, and Asymptotic Behavior
We study a multiperiod demand response management problem in the smart ...
read it

On the Analysis of the DeGrootFriedkin Model with Dynamic Relative Interaction Matrices
This paper analyses the DeGrootFriedkin model for evolution of the indi...
read it

Ease.ml: Towards Multitenant Resource Sharing for Machine Learning Workloads
We present ease.ml, a declarative machine learning service platform we b...
read it

Countries' Survival in Networked International Environments
This paper applies a recently developed power allocation game in Li and ...
read it

Evolution of Social Power in Social Networks with Dynamic Topology
The recently proposed DeGrootFriedkin model describes the dynamical evo...
read it

A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for PositiveUnlabeled Classification
The positiveunlabeled (PU) classification is a common scenario in real...
read it

D^2: Decentralized Training over Decentralized Data
While training a machine learning model using multiple workers, each of ...
read it

Decentralization Meets Quantization
Optimizing distributed learning systems is an art of balancing between c...
read it

Multidevice, Multitenant Model Selection with GPEI
Bayesian optimization is the core technique behind the emergence of Auto...
read it

Learning Simple Thresholded Features with Sparse Support Recovery
The thresholded feature has recently emerged as an extremely efficient, ...
read it

GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning
Graph embedding is a central problem in social network analysis and many...
read it

DiscreteTime Polar Opinion Dynamics with Susceptibility
This paper considers a discretetime opinion dynamics model in which eac...
read it

EndtoEnd Learning of EnergyConstrained Deep Neural Networks
Deep Neural Networks (DNN) are increasingly deployed in highly energyco...
read it

Marginal Policy Gradients for Complex Control
Many complex domains, such as robotics control and realtime strategy (R...
read it

Gradient Sparsification for CommunicationEfficient Distributed Optimization
Modern large scale machine learning applications require stochastic opti...
read it

Stochastically Controlled Stochastic Gradient for the Convex and Nonconvex Composition problem
In this paper, we consider the convex and nonconvex composition problem...
read it

Proximal Online Gradient is Optimum for Dynamic Regret
In online learning, the dynamic regret metric chooses the reference (opt...
read it

Revisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization
Batch Normalization (BN) has been used extensively in deep learning to a...
read it

Parametrized Deep QNetworks Learning: Reinforcement Learning with DiscreteContinuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider eith...
read it

PMCGS: Parallel Monte Carlo Acyclic Graph Search
Recently, there have been great interests in Monte Carlo Tree Search (MC...
read it

Stochastic PrimalDual Method for Empirical Risk Minimization with O(1) PerIteration Complexity
Regularized empirical risk minimization problem with linear predictor ap...
read it

Distributed Learning over Unreliable Networks
Most of today's distributed machine learning systems assume reliable ne...
read it

Dantzig Selector with an Approximately Optimal Denoising Matrix and its Application to Reinforcement Learning
Dantzig Selector (DS) is widely used in compressed sensing and sparse le...
read it