The paper studies a remote inference system that uses multimodal machine learning models to perform real‑time inference from features collected by remote sensors. It formulates a scheduling problem to minimize inference error, modeling error as a function of the Age of Information (AoI) vector, and solves it via a semi‑Markov decision process. The authors derive optimal policies for two‑modality and general multi‑modality cases, and propose low‑complexity alternatives that trade off speed and error.
arXiv:2609.24380v1 Announce Type: new Abstract: RLVR has substantially improved the reasoning capabilities of LLMs. However, existing methods typically parameterize temporal progression in the Markov...
arXiv:2610.09519v1 Announce Type: new Abstract: Production machine-learning models are derived artifacts of time-bounded training snapshots: a deployed model is a materialized view over a training cu...
arXiv:2607. 10694v1 Announce Type: cross Abstract: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device.
arXiv:2502. 11007v5 Announce Type: replace Abstract: Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities through multi-modal data sources and multi-turn conversations.
arXiv:2501. 12942v2 Announce Type: replace Abstract: Effective multi-user delay-constrained scheduling is crucial in various real-world applications, including embodied AI, instant messaging, live streaming, and data center management, where efficient resource allocation is required among users with diverse delay sensitivities.
arXiv:2607. 27626v1 Announce Type: new Abstract: Safety-critical IoT systems such as industrial closed-loop control, V2X coordination, and remote teleoperation require every sensor's peak Age of Information (peak AoI, also abbreviated PAoI) to stay below a hard per-slot deadline, not merely an average bound.
The paper introduces REP-PD-TEG, a representation‑learning algorithm for low‑rank continuous‑state constrained Markov Decision Processes (CMDPs) that achieves optimal ≥O(√K) regret in the soft cumulative‑violation setting while maintaining a ≥O(K^{3/4}) sample bound when exploratory actions are penalised. For the stricter hard cumulative‑violation scenario, REP-PD-H-TEG is proposed, which uses a bonus‑corrected lower‑confidence utility certificate and a stabilized dual search to guarantee both regret and hard‑violation bounds. Together, these methods provide the first theoretically guaranteed representation‑learning framework for low‑rank continuous‑state CMDPs with both soft and hard violation controls.
arXiv:2609. 14959v1 Announce Type: new Abstract: We study decentralized learning of Nash equilibria (NE) in infinite-horizon discounted Markov games under bandit feedback, focusing on Markov $\alpha$-potential games.
arXiv:2607. 20769v1 Announce Type: new Abstract: Learning-enabled decision systems often use offline data or computation to reduce online compute cost.
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.
The paper introduces Fast Regularized Policy Mirror Descent (PMD) that pairs policy updates with a single temporal-difference (TD) critic step. It proves global linear convergence for finite discounted MDPs using exact coordinate-wise Bellman updates and any positive actor stepsize, regardless of critic initialization. For stochastic TD-PMD with strongly convex mirror maps, the authors achieve an expected value gap of ε after “~O(1/((1-γ)^5 σ_b ε))” transitions, without requiring trajectory resets, generative models, or nested policy evaluation loops.
arXiv:2608. 09366v1 Announce Type: new Abstract: Large-scale learning systems often face the challenge of balancing multiple, potentially competing objectives, such as fairness, accuracy, and latency.