3 problems

Let $T$ be the time horizon, let the rounds be partitioned into batches $(\mathcal{T}_j)_{j=1}^n$ of size $Delta_T$, and let $V_{T,j}=\sum_{t\in\mathcal{T}_j}|m_t-m_{t-1}|$ denote…

State-dependent switching conjecture. Such an assumption could render the average dwell-time Assumption unnecessary.

Polynomial-variation regret conjecture. A similar algorithm based on these degree-$k$ monomial covariates can achieve optimal dynamic regret for comparators in the class…