arXiv:2608.16947v2 Announce Type: replace-cross
Abstract: Dynamic Mixture-of-Experts Serving allocates k replica GPUs among m experts as workloads change. At each round, the online algorithm sees the...
By Ian D'Ambrosio (Nth Research Collective)
arXiv:2608. 12134v1 Announce Type: cross Abstract: We study nonnegative submodular maximization subject to a general matroid when the offline algorithm is given an arbitrary controlled value oracle.
By Vaneet Aggarwal
arXiv:2603. 10346v2 Announce Type: replace Abstract: We study the fixed-budget best-arm identification (BAI) problem in non-stationary linear bandits.
By Leo Maynard-Zhang, Zhihan Xiong, Kevin Jamieson, Maryam Fazel
arXiv:2608. 01616v1 Announce Type: new Abstract: Competitive analysis is central to the study of online algorithms, but upper bounds are often highly problem-specific.
By Thomas Kesselheim, Marco Molinaro, Kalen Patton, Sahil Singla
The paper studies online convex optimization when the learner can only query an exact linear optimization oracle. It establishes a dimension‑free minimax expected regret bound of θ(GD max{√T, T/(1+min{Q,BT})^{1/4}}) for convex G‑Lipschitz losses, where Q is the total oracle budget and B the per‑round limit. The authors provide matching lower and upper bounds, showing how strict per‑round or total‑budget constraints affect the achievable regret, and extend the analysis to smooth losses with curvature‑dependent bounds.
By Vaneet Aggarwal
The paper revisits the Successive Rejects (SR) algorithm for best‑arm identification, showing that although SR appears non‑adaptive due to fixed phase lengths, it achieves an optimal worst‑instance error exponent for Gaussian arms with common variance. The authors formulate an optimization problem to design a phase schedule that maximizes the normalized error exponent, leading to a new variant called H1‑balanced Successive Rejects (H1‑SR). H1‑SR attains at least 11/12 of the optimal normalized rate for all K ≥ 2, approaching the optimum as K grows, and experiments demonstrate significant performance gains over the original SR while highlighting trade‑offs in early elimination strategies.
By Mohamed Khair, Junpei Komiyama