Lower Bounds For Gradient-Free Convex Optimization And Convex-Concave Saddle-Point Problems

We study the query complexity of optimization with exact scalar-value information. For globally $L$-smooth convex functions on ${\mathbb{R}}^d$ with a minimizer in a Euclidean ball of radius $R$, we prove the lower bound $\Omega (d\min \{d,\sqrt{L{R}^2/\epsilon }\})$ for adaptive randomized algorithms in the stated accuracy range. Queries are unrestricted, and the bound contains no logarithmic factor. It holds for quadratics and matches the minimum of two elementary upper bounds on that class. Prescribed strong convexity introduces the additional cap $\sqrt{L/\mu }$. The proof compares the mean of a matrix with the mean of its inverse on arbitrary affine slices and bounds posterior moments after adaptive measurements. We extend these information bounds to saddle-point problems with independent block dimensions. For compact bilinear games, the coupling alone yields $\Omega (r\min \{r,\sqrt{C{R}_x{R}_y/\epsilon }\})$ queries, where $r=\min \{d_x,d_y\}$. A strongly convex–strongly concave construction yields a condition-dependent lower bound even with known isotropic diagonal Hessians. Separate reductions establish scalar query lower bounds under mixed value and partial-gradient access, including for outer objective accuracy. A Euclidean-image radius yields smooth and nonsmooth extensions to independently specified norms and known penalties.