Tracking the Best Expert in Non-stationary Stochastic Environments

Abstract

We study the dynamic regret of multi-armed bandit and experts problem in non-stationary stochastic environments. We introduce a new parameter $Λ$, which measures the total statistical variance of the loss distributions over $T$ rounds of the process, and study how this amount affects the regret. We investigate the interaction between $Λ$ and $Γ$, which counts the number of times the distributions change, as well as $Λ$ and $V$, which measures how far the distributions deviates over time. One striking result we find is that even when $Γ$, $V$, and $Λ$ are all restricted to constant, the regret lower bound in the bandit setting still grows with $T$. The other highlight is that in the full-information setting, a constant regret becomes achievable with constant $Γ$ and $Λ$, as it can be made independent of $T$, while with constant $V$ and $Λ$, the regret still has a $T^{1/3}$ dependency. We not only propose algorithms with upper bound guarantee, but prove their matching lower bounds as well.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 32 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.