Robust density estimation over star-shaped density classes

Abstract: We establish a novel criterion for comparing the performance of two densities, $g_1$ and $g_2$, within the context of corrupted data. Utilizing this criterion, we propose an algorithm to construct a density estimator within a star-shaped density class, $\mathcal{F}$, under conditions of data corruption. We proceed to derive the minimax upper and lower bounds for density estimation across this star-shaped density class, characterized by densities that are uniformly bounded above and below (in the sup norm), in the presence of adversarially corrupted data. Specifically, we assume that a fraction $\epsilon \leq \frac{1}{3}$ of the $N$ observations are arbitrarily corrupted. We obtain the minimax upper bound $$\max{ \tau_{\overline{J}}^2, \epsilon } \wedge d<sup>2$$. Under certain conditions, we obtain the minimax risk, up to proportionality constants, under the squared $L_2$ loss as $$ \max\left{ \tau^{*2} \wedge d^2, \epsilon \wedge d² \right}, $$ where $\tau^* := \sup\left{ \tau : N\tau² \leq \log \mathcal{M}<em>{\mathcal{F}}^{{\text{loc}}(\tau,} c) \right}$ for a sufficiently large constant $c$. Here, $$\mathcal{M}</em>{\mathcal{F}}^{{\text{loc}}(\tau,} c)$$ denotes the local entropy of the set $\mathcal{F}$, and $d$ is the $L_2$ diameter of $\mathcal{F}$.