Bilevel-Optimization

TL;DR for operators Neural architecture search is not simply a process for selecting layers, connections, and activation functions. It is a process for comparing trained architecture–weight pairs. That distinction matters because an architecture evaluated with poorly optimized weights may look worse than an inferior architecture whose weights happened to train faster. A search system can therefore become very efficient at ranking the wrong candidates. ...

Routes look clean on a dashboard. A line leaves the depot, touches a sequence of customers, maybe bends toward a charging station, and returns home. The illusion is that route planning is still mostly about drawing the shortest useful line. Electric fleets ruin that illusion rather quickly. A diesel truck can treat refueling as an annoying but usually minor detail. An electric vehicle cannot. Battery capacity turns distance into feasibility. Charging stations turn geography into detours. A route that looks efficient before charging may become expensive after charging; a route that looks wasteful may avoid a much uglier charging pattern. This is why the Electric Capacitated Vehicle Routing Problem, or E-CVRP, is not merely the old vehicle-routing problem wearing a green jacket. It is a coupled routing-and-energy problem, and coupling is where algorithms go to lose their innocence. ...