arXiv:2608. 16947v1 Announce Type: cross Abstract: Huang, Lou, and Xiao introduced Dynamic Mixture-of-Experts Serving and gave an O(sqrt(log k))-competitive randomized algorithm for its integral primal problem, where k is the number of replica GPUs beyond the mandatory copy of each expert.
arXiv:2608.12134v2 Announce Type: replace-cross Abstract: We study nonnegative submodular maximization on $n$ elements subject to a general matroid of rank $k$, when the offline algorithm is given an...
arXiv:2603. 00910v2 Announce Type: replace-cross Abstract: Layer-wise capacity in large language models is highly non-uniform: some layers contribute disproportionately to loss reduction, whereas others are nearly redundant.
The paper studies how to allocate a fixed computational budget across the denoising steps of diffusion models to improve sample quality at deployment. It shows that the expected benefit of evaluating multiple candidates at a step can be decomposed into a step‑specific sensitivity and a universal sample‑size factor, and that the optimal allocation follows a water‑filling structure. Experiments demonstrate that this allocation achieves the same quality as a uniform strategy while reducing function evaluations by 20–50%.
The paper addresses an online resource allocation problem where a budget must be distributed among multiple arms under censored feedback. Each arm yields a reward only if it is activated by an unknown Bernoulli process and the allocated budget exceeds a random threshold from an unknown parametric distribution. The authors establish a worst‑case regret lower bound of Σ(√T), propose the RA‑UCB algorithm achieving near‑optimal regret when the budget is known, and introduce MG‑UCB for unknown, round‑dependent budgets, validating both approaches experimentally.
The paper proposes a method for routing requests to a fixed pool of quantized Mixture-of-Experts (MoE) instances, aiming to maximize throughput while respecting a quality‑degradation budget. It introduces Fragility‑Weighted Perplexity (FWP) as a request‑specific risk metric derived from prompt tokens, and uses a window‑level linear program to compute a reduced‑reward score that aligns with the LP optimum. Experiments on Qwen prompts show that FWP‑based allocation improves throughput by 2.5% over request‑agnostic mixing and static configurations.
arXiv:2610. 04049v2 Announce Type: replace-cross Abstract: We study the maximization of a nonnegative $k$-submodular function, not assumed monotone, in which each of $n$ elements receives one of $k\ge2$ labels or stays unselected and the selected elements must satisfy a constraint.
arXiv:2610. 19179v1 Announce Type: cross Abstract: We study packet routing in queuing systems where queues act as selfish, myopic agents that use no-regret learning algorithms to select servers with unknown service rates.
The paper investigates TCP acknowledgment strategies that aim to minimize both acknowledgment and waiting costs. It establishes that no deterministic online algorithm can achieve a competitive ratio better than 2, and shows that achieving sublinear regret requires at least $k$ randomized online experts.
arXiv:2610. 13924v1 Announce Type: new Abstract: A parallel sampler can choose at random which coordinates to generate together.
arXiv:2608. 07747v1 Announce Type: new Abstract: We study how to share a single conserved capacity budget across many locations and two service classes when demand is uneven, time-varying, and can exceed supply.
arXiv:2609. 21523v2 Announce Type: replace Abstract: A state may need to be compressed before its exact downstream task is known.