A sharp lower bound is proved for smooth nonconvex stochastic optimization with uniformly bounded gradient noise with uniformly bounded gradient noise and resolves the question raised by whether almost-surely bounded oracle error permits a better rate than bounded variance.
Abstract
We prove a sharp lower bound for smooth nonconvex stochastic optimization with uniformly bounded gradient noise. In the \(K=1\) fresh-sample model, every randomized adaptive algorithm requires $$\Omega\left( \frac{\Delta L}{\epsilon^2} + \frac{\Delta L\sigma^2}{\epsilon^4} \right)$$ queries to find a point with expected gradient norm at most \(\epsilon\). This matches the standard upper bound and, to the best of our knowledge, resolves the question raised by [Arjevani et al. 2023] of whether almost-surely bounded oracle error permits a better rate than bounded variance. The proof was independently generated with GPT-5.6 Sol in Codex's Ultra mode during a two-hour session. The human author supplied the prompt and was responsible only forchecking the proof and revising and polishing the manuscript.
Whether exact scalar feedback intrinsically incurs the additional dimension $d$ paid by known zeroth-order methods remains open even for Lipschitz convex optimization. For a universal Lipschitz scale, the value only bound $O(d^2\log(d+1)\log(1/\epsilon))$ and two-point bound $O(d\epsilon^{-2})$ yield the upper bound $\widetilde O\left(d\min\{d,\epsilon^{-2}\}\right)$. By contrast, prior lower bounds for arbitrary randomized algorithms give only $\Omega(\min\{d,\epsilon^{-2}\})$, leaving a factor $d$ unexplained. We close this gap, up to logarithmic factors, for arbitrary adaptive randomized algorithms minimizing a convex objective with a universal Lipschitz scale over the $d$-dimensional Euclidean unit ball, where each query returns only the exact scalar value. Let $T_\epsilon$ denote the minimum number of queries required to return an $\epsilon$-suboptimal point with probability at least $1/2$, uniformly over the function class. We prove that \[T_\epsilon\ge c\,\frac{d\min\{d,\epsilon^{-2}\}}{\log\!\bigl(\min\{d,\epsilon^{-2}\}\bigr)},\] for $d\ge d_0$ and $0<\epsilon\le\epsilon_0$, where $c,\epsilon_0>0$ and $d_0\in\mathbb N$ are universal constants. This gives $\Omega\left(\frac{d}{\epsilon^2\log(1/\epsilon)}\right)$ in the low-accuracy regime $\epsilon\ge d^{-1/2}$ and $\Omega\left(\frac{d^2}{\log d}\right)$ in the high-accuracy regime $\epsilon\le d^{-1/2}$ with the latter independent of $\epsilon$. These bounds match the corresponding upper bound up to logarithmic factors. To our knowledge, this is the first near-optimal lower bound for arbitrary adaptive randomized algorithms throughout both accuracy regimes of exact value Lipschitz convex optimization. The proof uses a random support function hard family and develops a posterior mean energy method for adaptive exact max observations, in place of first-order zero chain constructions and noise based transcript inequalities.
Haihan Zhang, Chenheng Zhang, Zhiquan Qi et al.· 0 citations
It is proved that every deterministic first-order algorithm requires a first-order oracle that returns both the function value and the full subdifferential at every query point, and establishes the optimal deterministic oracle complexity.
We study the deterministic first-order oracle complexity of finding stationary points of the value function in smooth nonconvex-Polyak-{\L}ojasiewicz (NC-P{\L}) minimax optimization. We assume that the objective is jointly $\ell$-smooth and satisfies the $\mu$-P{\L} condition in the dual variable, and that its value function $\Phi(x):=\max_y f(x;y)$ satisfies $\Phi(0)-\inf_x\Phi(x)\leq\Delta$. When $\kappa:=\ell/\mu\gtrsim 1$ and $0<\epsilon^2\lesssim\ell\Delta$, we prove that every deterministic first-order method requires $\Omega(\ell\Delta\kappa/\epsilon^2)$ oracle queries in the worst case to find $x$ satisfying $\|\nabla\Phi(x)\|\leq\epsilon$. This rate matches the known upper bound in its dependence on $(\ell,\Delta,\kappa,\epsilon)$ [Yang et al., 2022] and shows that the linear dependence on $\kappa$ is unavoidable for deterministic first-order methods.
A variant of stochastic gradient descent with initial regularization with initial regularization is analyzed and dimension-free upper bounds on its expected excess risk for the squared loss are derived.
A lower bound of $\Omega(\,\frac{d^2}{\log(d+1)})$ on the oracle complexity in this setting is provided, to close this gap dating back to 1996, up to polylogarithmic factors.
A variant of the cubic-regularized Newton method for nonconvex optimization that is parameter-free in that it requires no prior knowledge of problem-dependent parameters is analyzed, and an oracle complexity bound is derived for finding an $(varepsilon, \delta)-second-order stationary point.