The paper presents a two‑level framework for portfolio management that selects window sizes in a cost‑sensitive, online manner. Candidate window sizes are treated as experts, and their aggregation weights are updated dynamically using turnover‑inclusive losses. The authors derive finite‑horizon tracking‑regret bounds that incorporate portfolio turnover, showing that with bounded losses and cost rates, a tuned Fixed Share algorithm achieves asymptotically no tracking regret for sublinear switching budgets, while Hedge handles the static case.
arXiv:2606. 08977v1 Announce Type: new Abstract: Motivated by the recency effect in online learning, we study algorithms for single-pass *sliding-window streaming multi-armed bandits (MABs)* in this paper.
By Vladimir Braverman, Chen Wang, Liudeng Wang, Samson Zhou
The paper introduces a straightforward framework that transforms dynamic regret minimization into switching regret minimization by constructing an unbiased random sequence for any comparator sequence. Using this reduction, the authors derive dynamic regret bounds for strongly convex and exp-concave losses of “~O(T^{1/3}P_T^{2/3})” and for general convex losses of “O(√{T(1+P_T)})”, matching known minimax optimal results. The approach leverages off-the-shelf switching regret algorithms and controlled variance to achieve these bounds.
By Yibo Wang, Wenhao Yang, Sifan Yang, Yuanyu Wan, Lijun Zhang
arXiv:2512. 09850v2 Announce Type: replace Abstract: We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty.
By Simone Cuonzo, Nina Deliu
arXiv:2609.07566v1 Announce Type: new
Abstract: Caching systems often rely on simple eviction policies such as Least Recently Used (LRU) and Least Frequently Used (LFU), which perform well in complem...
By Younes Ben Mazziane, Xinying Zou
arXiv:2601.13519v4 Announce Type: replace-cross
Abstract: This paper introduces a new problem-dependent regret measure for online convex optimization with smooth losses. The notion, which we call the...
By Wenzhi Gao, Chang He, Madeleine Udell
arXiv:2602.08372v2 Announce Type: replace
Abstract: We study dynamic regret minimization in non-stationary online learning, with a primary focus on follow-the-regularized-leader (FTRL) methods. FTRL...
By Yan-Feng Xie, Yu-Jie Zhang, Peng Zhao, Zhi-Hua Zhou
arXiv:2609. 30556v1 Announce Type: new Abstract: We study dynamic regret in online convex optimization with an \emph{indicator switching cost}: a fixed penalty incurred whenever two consecutive decisions differ.
By Naram Mhaisen, George Iosifidis
arXiv:2606. 04305v1 Announce Type: new Abstract: We study online learning with an additional offline dataset in the stochastic linear bandit setting.
By Kushagra Chandak, Toshinori Kitamura, Xiaoqi Tan
arXiv:2607. 00581v1 Announce Type: new Abstract: Sparse tangent portfolio optimization aims to learn an interpretable, low-cardinality portfolio in the tangency direction of the mean-variance frontier.
By Haeun Jeon, Seunghoon Choi, Hyunglip Bae, Yongjae Lee, Woo Chang Kim
arXiv:2606. 03831v1 Announce Type: new Abstract: This paper investigates non-stationary online learning using the metric of interval regret, which requires an online algorithm to perform well over every time interval.
By Yan-Feng Xie, Shuche Wang, Peng Zhao, Zhi-Hua Zhou
arXiv:2606. 03704v1 Announce Type: new Abstract: Financial decision-making tasks such as stock recommendation and portfolio allocation typically estimate future return and risk and then select trades or allocations for an investor, and the chosen optimization objective often determines realized performance.
By Keigo Sakurai, Takahiro Ogawa, Miki Haseyama, Anjyu Anan, Kei Nakagawa