Shapiro A Lectures On Stochastic Programming Crack [portable]ed | LATEST ★ |

| Concept | Misunderstood as | Shapiro’s "Cracked" Clarification | |--------|------------------|-------------------------------------| | SAA | Just average the samples and solve | Needs multiple runs to estimate optimality gap | | Recourse function | Smooth and differentiable | Often subdifferentiable — use subgradients | | Convergence | Always fast | Depends on problem dimension and tail behavior | | Risk aversion | Just add variance | Use coherent risk measures (CVaR) | | Stability | Minor issue | Central — use sensitivity analysis |