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

Principled Exploration via Optimistic Bootstrapping and Backward Induction
One principled approach for provably efficient exploration is incorporat...
read it

Machine learning spatiotemporal epidemiological model to evaluate Germanycountylevel COVID19 risk
As the COVID19 pandemic continues to ravage the world, it is of critica...
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

Variational Dynamic for SelfSupervised Exploration in Deep Reinforcement Learning
Efficient exploration remains a challenging problem in reinforcement lea...
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

On the Global Optimality of ModelAgnostic MetaLearning
Modelagnostic metalearning (MAML) formulates metalearning as a bileve...
read it

Provably Efficient Causal Reinforcement Learning with Confounded Observational Data
Empowered by expressive function approximators such as neural networks, ...
read it

Breaking the Curse of Many Agents: Provable Mean Embedding QIteration for MeanField Reinforcement Learning
Multiagent reinforcement learning (MARL) achieves significant empirical...
read it

Revisiting Membership Inference Under Realistic Assumptions
Membership inference attacks on models trained using machine learning ha...
read it

Efficient PrivacyPreserving Nonconvex Optimization
While many solutions for privacypreserving convex empirical risk minimi...
read it

A Knowledge Transfer Framework for Differentially Private Sparse Learning
We study the problem of estimating high dimensional models with underlyi...
read it

Neural Policy Gradient Methods: Global Optimality and Rates of Convergence
Policy gradient methods with actorcritic schemes demonstrate tremendous...
read it

Learning Onehiddenlayer ReLU Networks via Gradient Descent
We study the problem of learning onehiddenlayer neural networks with R...
read it

DeepDeblur: Fast onestep blurry face images restoration
We propose a very fast and effective onestep restoring method for blurr...
read it

Robust Wirtinger Flow for Phase Retrieval with Arbitrary Corruption
We consider the phase retrieval problem of recovering the unknown signal...
read it

A Nonconvex Free Lunch for LowRank plus Sparse Matrix Recovery
We study the problem of lowrank plus sparse matrix recovery. We propose...
read it

A Universal Variance ReductionBased Catalyst for Nonconvex LowRank Matrix Recovery
We propose a generic framework based on a new stochastic variancereduce...
read it

Stochastic Variancereduced Gradient Descent for Lowrank Matrix Recovery from Linear Measurements
We study the problem of estimating lowrank matrices from linear measure...
read it

A Unified Computational and Statistical Framework for Nonconvex LowRank Matrix Estimation
We propose a unified framework for estimating lowrank matrices through ...
read it
Lingxiao Wang
is this you? claim profile