An algorithm for online resource allocation with budget and general constraints achieves O(sqrt(T)) regret in stochastic and alpha-regret in adversarial regimes with bounded constraint violations.
Operations Research , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
BalanceRoute uses a piecewise-linear F-score (with optional short lookahead) for sticky request routing in LLM serving, reducing DP imbalance and raising end-to-end throughput versus vLLM baselines on production and Azure traces.
LLM serving requires mathematical optimization and algorithms with provable guarantees rather than generic heuristics that fail unpredictably on LLM workloads.
citing papers explorer
-
Online Resource Allocation With General Constraints
An algorithm for online resource allocation with budget and general constraints achieves O(sqrt(T)) regret in stochastic and alpha-regret in adversarial regimes with bounded constraint violations.
-
Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
BalanceRoute uses a piecewise-linear F-score (with optional short lookahead) for sticky request routing in LLM serving, reducing DP imbalance and raising end-to-end throughput versus vLLM baselines on production and Azure traces.
-
Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics
LLM serving requires mathematical optimization and algorithms with provable guarantees rather than generic heuristics that fail unpredictably on LLM workloads.