Online Resource Allocation with Convex-set Machine-Learned Advice

ArXi:2306.12282v2 Announce Type: replace-cross Decision-makers often have access to machine-learned predictions about future demand that can help guide online resource allocation decisions. However, such predictions may be inaccurate. We develop a framework for online resource allocation with potentially unreliable machine-learned advice, where the advice is represented as a convex uncertainty set for the demand vector rather than a single point estimate. Our approach extends classical protection-level algorithms by