Online composite optimization between stochastic and adversarial environments

Y Wang, S Chen, W Jiang, W Yang… - Advances in Neural …, 2025 - proceedings.neurips.cc
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 …

Distributed projection-free online learning for smooth and convex losses

Y Wang, Y Wan, S Zhang, L Zhang - … of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
We investigate the problem of distributed online convex optimization with complicated
constraints, in which the projection operation could be the computational bottleneck. To …

Improved dynamic regret for online frank-wolfe

Y Wan, L Zhang, M Song - The Thirty Sixth Annual …, 2023 - proceedings.mlr.press
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 …

Adaptive, doubly optimal no-regret learning in strongly monotone and exp-concave games with gradient feedback

M Jordan, T Lin, Z Zhou - Operations Research, 2024 - pubsonline.informs.org
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 …

[PDF][PDF] Towards fair disentangled online learning for changing environments

C Zhao, F Mi, X Wu, K Jiang, L Khan, C Grant… - Proceedings of the ACM …, 2023 - par.nsf.gov
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 …

Adaptive fairness-aware online meta-learning for changing environments

C Zhao, F Mi, X Wu, K Jiang, L Khan… - Proceedings of the 28th …, 2022 - dl.acm.org
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 …

Continuous diagnosis and prognosis by controlling the update process of deep neural networks

C Sun, H Li, M Song, D Cai, B Zhang, S Hong - Patterns, 2023 - cell.com
Continuous diagnosis and prognosis are essential for critical patients. They can provide
more opportunities for timely treatment and rational allocation. Although deep-learning …

Revisiting smoothed online learning

L Zhang, W Jiang, S Lu, T Yang - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …

A survey of controllable learning: Methods and applications in information retrieval

C Shen, X Zhang, T Shi, C Zhang, G **e… - arxiv preprint arxiv …, 2024 - arxiv.org
Controllable learning (CL) emerges as a critical component in trustworthy machine learning,
ensuring that learners meet predefined targets and can adaptively adjust without retraining …

Non-stationary projection-free online learning with dynamic and adaptive regret guarantees

Y Wang, W Yang, W Jiang, S Lu, B Wang… - Proceedings of the …, 2024 - ojs.aaai.org
Projection-free online learning has drawn increasing interest due to its efficiency in solving
high-dimensional problems with complicated constraints. However, most existing projection …