
A Unified OffPolicy Evaluation Approach for General Value Function
General Value Function (GVF) is a powerful tool to represent both the pr...
read it

Provably Faster Algorithms for Bilevel Optimization
Bilevel optimization has been widely applied in many important machine l...
read it

Doubly Robust OffPolicy ActorCritic: Convergence and Optimality
Designing offpolicy reinforcement learning algorithms is typically a ve...
read it

Proximal Gradient DescentAscent: Variable Convergence under KŁ Geometry
The gradient descentascent (GDA) algorithm has been widely applied to s...
read it

Lower Bounds and Accelerated Algorithms for Bilevel Optimization
Bilevel optimization has recently attracted growing interests due to its...
read it

A Primal Approach to Constrained Policy Optimization: Global Optimality and FiniteTime Analysis
Safe reinforcement learning (SRL) problems are typically modeled as cons...
read it

Sample Complexity Bounds for Two Timescale Valuebased Reinforcement Learning Algorithms
Two timescale stochastic approximation (SA) has been widely used in valu...
read it

Provably Faster Algorithms for Bilevel Optimization and Applications to MetaLearning
Bilevel optimization has arisen as a powerful tool for many machine lear...
read it

FiniteTime Analysis for Double Qlearning
Although Qlearning is one of the most successful algorithms for finding...
read it

Spectral Algorithms for Community Detection in Directed Networks
Community detection in large social networks is affected by degree heter...
read it

Momentum Qlearning with FiniteSample Convergence Guarantee
Existing studies indicate that momentum ideas in conventional optimizati...
read it

Feedback Capacities of Gaussian MultipleAccess Wiretap Channels
The feedback capacities of the Gaussian multipleaccess channel (GMAC) a...
read it

Analysis of Qlearning with Adaptation and Momentum Restart for Gradient Descent
Existing convergence analyses of Qlearning mostly focus on the vanilla ...
read it

When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence
Generative adversarial imitation learning (GAIL) is a popular inverse re...
read it

Convergence of MetaLearning with TaskSpecific Adaptation over Partial Parameters
Although modelagnostic metalearning (MAML) is a very successful algori...
read it

Enhanced First and Zeroth Order Variance Reduced Algorithms for MinMax Optimization
Minmax optimization captures many important machine learning problems s...
read it

Nonasymptotic Convergence Analysis of Two Timescale (Natural) ActorCritic Algorithms
As an important type of reinforcement learning algorithms, actorcritic ...
read it

Improving Sample Complexity Bounds for ActorCritic Algorithms
The actorcritic (AC) algorithm is a popular method to find an optimal p...
read it

Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization
Various types of parameter restart schemes have been proposed for accele...
read it

MultiStep ModelAgnostic MetaLearning: Convergence and Improved Algorithms
As a popular metalearning approach, the modelagnostic metalearning (M...
read it

Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack
The multiarmed bandit formalism has been extensively studied under vari...
read it

Nonasymptotic Convergence of Adamtype Reinforcement Learning Algorithms under Markovian Sampling
Despite the wide applications of Adam in reinforcement learning (RL), th...
read it

Reanalysis of Variance Reduced Temporal Difference Learning
Temporal difference (TD) learning is a popular algorithm for policy eval...
read it

Improved ZerothOrder Variance Reduced Algorithms and Analysis for Nonconvex Optimization
Two types of zerothorder stochastic algorithms have recently been desig...
read it

Faster Stochastic Algorithms via HistoryGradient Aided Batch Size Adaptation
Various schemes for adapting batch size have been recently proposed to a...
read it

Distributed SGD Generalizes Well Under Asynchrony
The performance of fully synchronized distributed systems has faced a bo...
read it

Two Timescale OffPolicy TD Learning: Nonasymptotic Analysis over Markovian Samples
Gradientbased temporal difference (GTD) algorithms are widely used in o...
read it

Momentum Schemes with Stochastic Variance Reduction for Nonconvex Composite Optimization
Two new stochastic variancereduced algorithms named SARAH and SPIDER ha...
read it

FiniteSample Analysis for SARSA and QLearning with Linear Function Approximation
Though the convergence of major reinforcement learning algorithms has be...
read it

SGD Converges to Global Minimum in Deep Learning via Starconvex Path
Stochastic gradient descent (SGD) has been found to be surprisingly effe...
read it

MRGAN: Manifold Regularized Generative Adversarial Networks
Despite the growing interest in generative adversarial networks (GANs), ...
read it

Minimax Estimation of Neural Net Distance
An important class of distance metrics proposed for training generative ...
read it

SpiderBoost: A Class of Faster Variancereduced Algorithms for Nonconvex Optimization
There has been extensive research on developing stochastic variance redu...
read it

Cubic Regularization with Momentum for Nonconvex Optimization
Momentum is a popular technique to accelerate the convergence in practic...
read it

A Note on Inexact Condition for Cubic Regularized Newton's Method
This note considers the inexact cubicregularized Newton's method (CR), ...
read it

Convergence of Cubic Regularization for Nonconvex Optimization under KL Property
Cubicregularized Newton's method (CR) is a popular algorithm that guara...
read it

Kmedoids Clustering of Data Sequences with Composite Distributions
This paper studies clustering of data sequences using the kmedoids algo...
read it

Parallel Gaussian Channels Corrupted by Independent States With a StateCognitive Helper
We consider a statedependent parallel Gaussian channel with independent...
read it

Convergence of SGD in Learning ReLU Models with Separable Data
We consider the binary classification problem in which the objective fun...
read it

StateDependent Interference Channel with Correlated States
This paper investigates the Gaussian statedependent interference channe...
read it

Sample Complexity of Stochastic VarianceReduced Cubic Regularization for Nonconvex Optimization
The popular cubic regularization (CR) method converges with first and s...
read it

Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization
The success of deep learning has led to a rising interest in the general...
read it

Local Geometry of OneHiddenLayer Neural Networks for Logistic Regression
We study the local geometry of a onehiddenlayer fullyconnected neural...
read it

Secrecy Capacity of Colored Gaussian Noise Channels with Feedback
In this paper, the kth order autoregressive moving average (ARMA(k)) Ga...
read it

Nonparametric Composite Hypothesis Testing in an Asymptotic Regime
We investigate the nonparametric, composite hypothesis testing problem f...
read it

Critical Points of Neural Networks: Analytical Forms and Landscape Properties
Due to the success of deep learning to solving a variety of challenging ...
read it

Characterization of Gradient Dominance and Regularity Conditions for Neural Networks
The past decade has witnessed a successful application of deep learning ...
read it

Nonconvex LowRank Matrix Recovery with Arbitrary Outliers via MedianTruncated Gradient Descent
Recent work has demonstrated the effectiveness of gradient descent for d...
read it

Reshaped Wirtinger Flow and Incremental Algorithm for Solving Quadratic System of Equations
We study the phase retrieval problem, which solves quadratic system of e...
read it

Nonparametric Detection of Geometric Structures over Networks
Nonparametric detection of existence of an anomalous structure over a ne...
read it
Yingbin Liang
is this you? claim profile
Associate Professor, Electrical & Computer Engineering at The Ohio State University