Dri-MED achieves Õ(κ d² log T / Δ̃) regret and Õ(d) constraint violations for drifting contextual bandits with personalized preferences and baseline constraints under practitioner-friendly assumptions.
arXiv preprint arXiv:2503.12020 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts
Dri-MED achieves Õ(κ d² log T / Δ̃) regret and Õ(d) constraint violations for drifting contextual bandits with personalized preferences and baseline constraints under practitioner-friendly assumptions.