We adopt a policy optimization viewpoint towards policy evaluation for r...
We consider a class of stochastic smooth convex optimization problems un...
Optimization problems involving sequential decisions in a stochastic
env...
Designing computationally efficient exploration strategies for on-policy...
Reinforcement learning (RL) problems over general state and action space...
Risk and sparsity requirements often need to be enforced simultaneously ...
We consider the problem of solving robust Markov decision process (MDP),...
We study the problem of average-reward Markov decision processes (AMDPs)...
Attention to data-driven optimization approaches, including the well-kno...
We propose the homotopic policy mirror descent (HPMD) method for solving...
In this paper, we present a new class of policy gradient (PG) methods, n...
We study the problem of policy evaluation with linear function approxima...
The problem of constrained Markov decision process (CMDP) is investigate...
Embedding learning has found widespread applications in recommendation
s...
We present new policy mirror descent (PMD) methods for solving reinforce...
The focus of this paper is on stochastic variational inequalities (VI) u...
Safe reinforcement learning (SRL) problems are typically modeled as
cons...
In this paper we first present a novel operator extrapolation (OE) metho...
Nonconvex sparse models have received significant attention in
high-dime...
Conditional gradient methods have attracted much attention in both machi...
Much recent research effort has been directed to the development of effi...
Stochastic dual dynamic programming is a cutting plane type algorithm fo...
Nonconvex optimization is becoming more and more important in machine
le...
Recovering sparse conditional independence graphs from data is a fundame...
We propose a novel randomized incremental gradient algorithm, namely,
VA...
Momentum is a popular technique to accelerate the convergence in practic...
Stochastic gradient descent (Sgd) methods are the most powerful
optimiza...
In this paper, we explore some basic questions on the complexity of trai...
In this work, we introduce an asynchronous decentralized accelerated
sto...
This note considers the inexact cubic-regularized Newton's method (CR), ...
The popular cubic regularization (CR) method converges with first- and
s...
In this paper, we consider a class of finite-sum convex optimization pro...
In this paper, we consider multi-stage stochastic optimization problems ...
In this work we introduce a conditional accelerated lazy stochastic grad...
This paper considers the problem of minimizing an expectation function o...
In this paper, we present a generic framework to extend existing uniform...
In this paper, we consider a class of finite-sum convex optimization pro...
In this paper, we introduce a new stochastic approximation (SA) type
alg...