Network slicing plays a crucial role in realizing 5G/6G advances, enabling diverse Service Level Agreement (SLA) requirements related to latency, throughput, and reliability. Since network slices are deployed end-to-end (E2E), across multiple domains including access, transport, and core networks, it is essential to efficiently decompose an E2E SLA into domain-level targets, so that each domain can provision adequate resources for the slice. However, decomposing SLAs is highly challenging due to the heterogeneity of domains, dynamic network conditions, and the fact that the SLA orchestrator is oblivious to the domain's resource optimization. In this work, we propose Odin, a Bayesian Optimization-based solution that leverages each domain's online feedback for provably-efficient SLA decomposition. Through theoretical analyses and rigorous evaluations, we demonstrate that Odin's E2E orchestrator can achieve up to 45% performance improvement in SLA satisfaction when compared with baseline solutions whilst reducing overall resource costs even in the presence of noisy feedback from the individual domains.

In this paper, we study the multi-armed bandit problem in the best-of-both-worlds (BOBW) setting with heavy-tailed losses, where the losses can be negative and unbounded but have $(1+v)$-th raw moments bounded by $u^{1+v}$ for some known $u>0$ and $v\in(0,1]$. Specifically, we consider the BOBW setting where the underlying environment could be either (oblivious) adversarial (i.e., the loss distribution can change arbitrarily over time) or stochastic (i.e., the loss distribution is fixed over time) and is unknown to the decision-maker a prior, and propose an algorithm that achieves a $T^{\frac{1}{1+v}}$-type worst-case (pseudo-)regret in the adversarial regime and a $\log T$-type gap-dependent regret in the stochastic regime, where $T$ is the time horizon. Compared to the state-of-the-art results, our algorithm offers stronger \emph{high-probability} regret guarantees rather than expected regret guarantees, and more importantly, relaxes a strong technical assumption on the loss distribution. This assumption is needed even for the weaker expected regret obtained in the literature and is generally hard to verify in practice. As a byproduct, relaxing this assumption leads to the first near-optimal regret result for heavy-tailed bandits with Huber contamination in the adversarial regime, in contrast to all previous works focused on the (easier) stochastic regime. Our result also implies a high-probability BOBW regret guarantee when the bounded true losses are protected with pure Local Differential Privacy (LDP), while the existing work ensures the (weaker) \emph{approximate} LDP with the regret bounds in expectation only.

In this paper, we study the role of feedback in online learning with switching costs. It has been shown that the minimax regret is $\widetilde{\Theta}(T^{2/3})$ under bandit feedback and improves to $\widetilde{\Theta}(\sqrt{T})$ under full-information feedback, where $T$ is the length of the time horizon. However, it remains largely unknown how the amount and type of feedback generally impact regret. To this end, we first consider the setting of bandit learning with extra observations; that is, in addition to the typical bandit feedback, the learner can freely make a total of $B_{\mathrm{ex}}$ *extra observations*. We fully characterize the minimax regret in this setting, which exhibits an interesting *phase-transition phenomenon*: when $B_{\mathrm{ex}} = O(T^{2/3})$, the regret remains $\widetilde{\Theta}(T^{2/3})$, but when $B_{\mathrm{ex}} = \Omega(T^{2/3})$, it becomes $\widetilde{\Theta}(T/\sqrt{B_{\mathrm{ex}}})$, which improves as the budget $B_{\mathrm{ex}}$ increases. To design algorithms that can achieve the minimax regret, it is instructive to consider a more general setting where the learner has a budget of $B$ *total* observations. We fully characterize the minimax regret in this setting as well and show that it is $\widetilde{\Theta}(T/\sqrt{B})$, which scales smoothly with the total budget $B$. Furthermore, we propose a generic algorithmic framework, which enables us to design different learning algorithms that can achieve matching upper bounds for both settings based on the amount and type of feedback. One interesting finding is that while bandit feedback can still guarantee optimal regret when the budget is relatively limited, it no longer suffices to achieve optimal regret when the budget is relatively large.

Motivated by the engineering application of efficient mobility management in ultra-dense wireless networks, we propose a novel cost-aware cascading bandit model with two-level actions. Compared with the standard cascading bandit model with a single-level action, this new model captures the real-world action sequence in mobility management, where the base station not only decides on an ordered neighbor cell list before measurement, but also executes the final handover decision to the target base station. We first analyze the optimal offline policy when the arm statistics are known beforehand. An online learning algorithm coined two-level Cost-aware Cascading UCB (CC-UCB) is then proposed to exploit the structure of the optimal offline policy with estimated arm statistics. Theoretical analysis shows that the cumulative regret under two-level CC-UCB scales logarithmically in time, which coincides with the asymptotic lower bound, thus is order-optimal. Simulation results corroborate the theoretical results and validate the effectiveness of two-level CC-UCB for mobility management.