Author

Ian D'Ambrosio

h-index 0 View on Semantic Scholar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

A Deterministic Constant-Competitive Algorithm for Dynamic Mixture-of-Experts Serving

Dynamic Mixture-of-Experts Serving allocates k replica GPUs among m experts as workloads change. At each round, the online algorithm sees the current workload, chooses integral replica counts, and pays bottleneck service cost plus replica movement. It does not know future workloads. Huang, Lou, and Xiao gave an O(sqrt(...

Ian D'Ambrosio · 0 citations

Preprint Aug 2026

A Tight Linear Deterministic Competitive Ratio for Fully Online KV-Cache Scheduling

A fully online model for batching nonpreemptive LLM requests under a growing KV-cache memory constraint and it is proved that every deterministic algorithm has competitive ratio Omega(sqrt(n), while the elementary sequential upper bound is n.

Ian D'Ambrosio · 0 citations

#machine learning Preprint Aug 2026

A Constant-Competitive Algorithm for Dynamic Mixture-of-Experts Serving

It is proved that the randomized primal competitive ratio is in fact Theta(1) for arbitrary numbers of experts and the upper bound reduces reciprocal-max service costs to chasing positive bodies with covering row sparsity two.

Ian D'Ambrosio · 0 citations