Budget-Aware Step Selection for Forward-Only Recovery of Analog Accelerators

Recovering a drifted analog accelerator with forward-only optimization costs queries both to update its parameters and to choose those updates. We study step selection under this combined cost. In a controlled testbed, measured single-step descent boundaries exceed whole-run failure boundaries by a geometric mean of $27.2\times$: initial progress alone is a poor guide to a full recovery run. We isolate accumulated readout noise, derive a finite-horizon displacement bound, and use its step scale to select a rate from donor-device measurements without searching on the target device. The resulting model captures observed noise and probe scaling, but overpredicts failure boundaries by $2.20\times$ in geometric mean; its budget dependence remains unresolved. On $36$ held-out simulated crossbar targets, a selector with a fine rate grid and donors matched by device condition uses $93.62\%$ fewer operational forward evaluations than target search, with a $0.399$ percentage-point accuracy deficit. A transferred condition-specific fixed setting is more accurate at lower incremental cost, showing that avoiding target search need not require donor measurements. Calibration uses clean simulator readout, and the bound concerns noise-only displacement, not device reliability. These results support evaluating recovery methods by both accuracy and configuration cost, with fixed transfer as an explicit comparator. An anonymous project page is available at https://dordlark158.github.io/budget-aware-step-selection/