TLDP is a nonparametric contextual dynamic pricing algorithm with provably minimax-optimal regret when source-domain data are available under covariate shift.
Since r(B) ≥ ˜r, it holds that P E c B ≤ exp n − 4−1CE κnP ˜rd+γ+1 o , (64) which completes the proof of (60)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Transfer Learning for Nonparametric Contextual Dynamic Pricing
TLDP is a nonparametric contextual dynamic pricing algorithm with provably minimax-optimal regret when source-domain data are available under covariate shift.