Online composite optimization between stochastic and adversarial environments
We study online composite optimization under the Stochastically Extended Adversarial
(SEA) model. Specifically, each loss function consists of two parts: a fixed non-smooth and …
(SEA) model. Specifically, each loss function consists of two parts: a fixed non-smooth and …
Distributed projection-free online learning for smooth and convex losses
We investigate the problem of distributed online convex optimization with complicated
constraints, in which the projection operation could be the computational bottleneck. To …
constraints, in which the projection operation could be the computational bottleneck. To …
Improved dynamic regret for online frank-wolfe
To deal with non-stationary online problems with complex constraints, we investigate the
dynamic regret of online Frank-Wolfe (OFW), which is an efficient projection-free algorithm …
dynamic regret of online Frank-Wolfe (OFW), which is an efficient projection-free algorithm …
Adaptive, doubly optimal no-regret learning in strongly monotone and exp-concave games with gradient feedback
Online gradient descent (OGD) is well-known to be doubly optimal under strong convexity or
monotonicity assumptions:(1) in the single-agent setting, it achieves an optimal regret of Θ …
monotonicity assumptions:(1) in the single-agent setting, it achieves an optimal regret of Θ …
[PDF][PDF] Towards fair disentangled online learning for changing environments
In the problem of online learning for changing environments, data are sequentially received
one after another over time, and their distribution assumptions may vary frequently. Although …
one after another over time, and their distribution assumptions may vary frequently. Although …
Adaptive fairness-aware online meta-learning for changing environments
The fairness-aware online learning framework has arisen as a powerful tool for the continual
lifelong learning setting. The goal for the learner is to sequentially learn new tasks where …
lifelong learning setting. The goal for the learner is to sequentially learn new tasks where …
Continuous diagnosis and prognosis by controlling the update process of deep neural networks
Continuous diagnosis and prognosis are essential for critical patients. They can provide
more opportunities for timely treatment and rational allocation. Although deep-learning …
more opportunities for timely treatment and rational allocation. Although deep-learning …
Revisiting smoothed online learning
In this paper, we revisit the problem of smoothed online learning, in which the online learner
suffers both a hitting cost and a switching cost, and target two performance metrics …
suffers both a hitting cost and a switching cost, and target two performance metrics …
A survey of controllable learning: Methods and applications in information retrieval
Controllable learning (CL) emerges as a critical component in trustworthy machine learning,
ensuring that learners meet predefined targets and can adaptively adjust without retraining …
ensuring that learners meet predefined targets and can adaptively adjust without retraining …
Non-stationary projection-free online learning with dynamic and adaptive regret guarantees
Projection-free online learning has drawn increasing interest due to its efficiency in solving
high-dimensional problems with complicated constraints. However, most existing projection …
high-dimensional problems with complicated constraints. However, most existing projection …