Conic programming has well-documented merits in a gamut of signal proces...
Meta-learning owns unique effectiveness and swiftness in tackling emergi...
Bayesian optimization (BO) has well-documented merits for optimizing
bla...
Semi-supervised learning (SSL) over graph-structured data emerges in man...
Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documen...
This paper presents our solution for the ICDAR 2021 Competition on Scien...
This paper studies the adversarial graphical contextual bandits, a varia...
Aiming at convex optimization under structural constraints, this work
in...
Few-shot image classification is challenging due to the lack of ample sa...
Recently, inspired by Transformer, self-attention-based scene text
recog...
We unveil the connections between Frank Wolfe (FW) type algorithms and t...
The main goal of this work is equipping convex and nonconvex problems wi...
Cascading bandit (CB) is a variant of both the multi-armed bandit (MAB) ...
Motivated by the widespread use of temporal-difference (TD-) and Q-learn...
The variance reduction class of algorithms including the representative ...
The main theme of this work is a unifying algorithm, abbreviated as L2S,...
The present paper considers leveraging network topology information to
i...
In the early history of positive-unlabeled (PU) learning, the sample
sel...
This paper studies bandit learning problems with delayed feedback, which...
To accommodate heterogeneous tasks in Internet of Things (IoT), a new
co...