Optimal control is notoriously difficult for stochastic nonlinear system...
Sliced Wasserstein (SW) distance suffers from redundant projections due ...
Deep latent variable models have achieved significant empirical successe...
Recent advances in Transformer architecture have empowered its empirical...
Representation learning often plays a critical role in reinforcement lea...
It is common to address the curse of dimensionality in Markov decision
p...
We propose a novel approach to the problem of clustering hierarchically
...
The Expectation-Maximization (EM) algorithm has been predominantly used ...
Using gradient descent (GD) with fixed or decaying step-size is standard...
In high-stake scenarios like medical treatment and auto-piloting, it's r...
It is known that when the statistical models are singular, i.e., the Fis...
Representation learning lies at the heart of the empirical success of de...
We study the statistical and computational complexities of the Polyak st...
Recent years have witnessed an upsurge of interest in employing flexible...
Deployed real-world machine learning applications are often subject to
u...
We revisit offline reinforcement learning on episodic time-homogeneous
t...
We consider the combinatorial bandits problem, where at each time step, ...
We propose to accelerate existing linear bandit algorithms to achieve
pe...
We consider off-policy evaluation (OPE), which evaluates the performance...
We propose a new Stein self-repulsive dynamics for obtaining diversified...
We propose MaxUp, an embarrassingly simple, highly effective technique
f...
Normalization methods such as batch normalization are commonly used in
o...
While Bayesian neural networks (BNNs) have drawn increasing attention, t...
Reward shaping is one of the most effective methods to tackle the crucia...
In this paper, we focus on solving two-player zero-sum extensive games w...
Automatically writing stylized Chinese characters is an attractive yet
c...