Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold

Despite the popularity of Adam optimizer in practice, most theoretical analyses study SGD as a proxy, and little is known about how the solutions found by Adam differ. In this paper, we show that Adam reduces a specific form of sharpness measure shaped by its adaptive updates, leading to qualitatively different solutions from SGD. When the training loss is small, Adam wanders around the manifold of minimizers and takes semi-gradients to minimize this sharpness measure in an adaptive manner, a behavior we rigorously characterize via a continuous-time approximation using stochastic differential equations. We further illustrate how this behavior differs from that of SGD in a well-studied setting: When training overparameterized models with label noise, SGD has been shown to minimize the trace of the Hessian matrix, $\text{tr}(\textbf{H})$, whereas we prove that Adam minimizes $\text{tr}(\text{Diag}(\textbf{H})^{1/2})$ instead. In solving sparse linear regression with diagonal linear networks, Adam provably achieves better sparsity and generalization than SGD due to this difference. Finally, we note that our proof framework applies not only to Adam but also to many other adaptive gradient methods, including but not limited to RMSProp, Adam-mini, and Adalayer. This provides a unified perspective for analyzing how adaptive optimizers reduce sharpness and may offer insights for future optimizer design.