Tight Analyses for Non-Smooth Stochastic Gradient Descent
share
Consider the problem of minimizing functions that are Lipschitz and strongly convex, but not necessarily differentiable. We prove that after T steps of stochastic gradient descent, the error of the final iterate is O((T)/T) with high probability. We also construct a function from this class for which the error of the final iterate of deterministic gradient descent is Ω((T)/T). This shows that the upper bound is tight and that, in this setting, the last iterate of stochastic gradient descent has the same general error rate (with high probability) as deterministic gradient descent. This resolves both open questions posed by Shamir (2012). An intermediate step of our analysis proves that the suffix averaging method achieves error O(1/T) with high probability, which is optimal (for any first-order optimization method). This improves results of Rakhlin (2012) and Hazan and Kale (2014), both of which achieved error O(1/T), but only in expectation, and achieved a high probability error bound of O((T)/T), which is suboptimal. We prove analogous results for functions that are Lipschitz and convex, but not necessarily strongly convex or differentiable. After T steps of stochastic gradient descent, the error of the final iterate is O((T)/√(T)) with high probability, and there exists a function for which the error of the final iterate of deterministic gradient descent is Ω((T)/√(T)).
READ FULL TEXT