This work proposes Think Short, Defer Smart (TSDS), a framework that synergistically integrates a lightweight convergence probe, which halts on-device reasoning once the intended action has stabilized, with a perplexity-based deferral rule that escalates uncertain actions to a cloud-side model.
This monograph presents a unified statistical framework for reliable post-training hyperparameter selection, centered on the learn-then-test (LTT) paradigm, that enables the choice of hyperparameters that provably satisfy application-specific reliability requirements.
The problem of maximizing the weighted average of performance certificates in the presence of uncertainty about the true system state is shown to be equivalent to an optimization over nested prediction sets, connecting to the literature on conformal prediction and extending prior art on single-level risk-averse decisio...
This work characterize the optimal policy under known distributions, and shows that it reduces to a prediction set-based solution for the CVaR, which provides an operational interpretation of conformal prediction-type prediction sets.
