Tag
This paper proposes a meta-learning framework for online convex optimization with indicator switching costs, achieving minimax-optimal dynamic regret bounds without prior knowledge of comparator variations.
FedPGT proposes a progressive gradient transmission scheme for vehicular federated learning to handle time-varying channels, achieving improved accuracy and reduced error in dynamic vehicular environments.
This paper presents distributed Riemannian online gradient descent on Hadamard manifolds with curvature-independent regret bounds for horospherical convex functions, achieving rates matching Euclidean optimization.
This paper presents an online algorithm for maximizing non-monotone DR-submodular functions under down-closed convex constraints, achieving the best-known offline approximation factor of 0.401 with sublinear regret in the full-information value-oracle model.
This paper introduces Director, a distributed MoE serving system that minimizes end-to-end latency using prediction-driven, online proactive expert placement. It employs a lightweight predictor and a relaxation-based optimizer to achieve up to 55% latency reduction for models like Mistral, DeepSeek, and Qwen.
This paper introduces a curvature-adaptive Follow-the-Perturbed-Leader (FTPL) algorithm for online optimization that achieves optimal regret bounds for both non-convex Lipschitz losses and strongly convex losses, using a time-varying perturbation scale.