We study the problem of experiment planning with function approximation in contextual bandit problems.

Statistical, 36(2):111-147, R. Sukkar hidden 2012 Medicine, pages Z. Sun, progression data.

Itisoften the responsibility of the agent designer toconstruct thistargetwhich,inrichandcomplexenvironments,constitutesaonerousburden; without full knowledge of the environment itself, a designer may forge a suboptimal learning target that poorly balances the amount ofinformation an agent must acquire to identify the target against the target's associated performance shortfall.

LoRA also exhibits concept-loss when multiple adapters are used concurrently.

Several popularly used FL algorithms for this setting includeFedAvg (McMahan et al., 2017), FedProx(Lietal.,2020b), We analyze its convergence behavior, expose problems, andpropose alternativesmore suitable forscaling upandgeneralization.