3 papers
stat.ML2026
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
Yang Xu, Jiefu Zhang, Haixiang Sun +3
Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-…
math.OC2025
DCatalyst: A Unified Accelerated Framework for Decentralized Optimization
Tianyu Cao, Xiaokai Chen, Gesualdo Scutari
We study decentralized optimization over a network of agents, modeled as graphs, with no central server. The goal is to minimize , where represents a (strongly) convex fun…
math.OC2024
Enhancing Convergence of Decentralized Gradient Tracking under the KL Property
Xiaokai Chen, Tianyu Cao, Gesualdo Scutari
We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a conve…