We thank the reviewers for the positive reviews and valuable feedback. Then, we reply to other remarks. We will update the manuscript accordingly. The idea of the proof is to combine the PL-inequality in Lemma 4.1 NTK is not well defined. On the contrary, our paper just requires the first layer to be overparameterized (i.e., all the As noted by Rev. 3, if Thus, GD requires more iterations to converge to a global optimum.

In this work, we consider the convergence of Polyak's heavy ball method, both in continuous and discrete time, on a non-convex objective function. We recover the convergence rates derived in [Pol64] for strongly convex objective functions, assuming only validity of the Polyak-Lojasiewicz inequality. In continuous time our result holds for all initializations, whereas in the discrete time setting we conduct a local analysis around the global minima. Our results demonstrate that the heavy ball method does, in fact, accelerate on the class of objective functions satisfying the Polyak-Lojasiewicz inequality. This holds even in the discrete time setting, provided the method reaches a neighborhood of the global minima. Instead of the usually employed Lyapunov-type arguments, our approach leverages a new differential geometric perspective of the Polyak-Lojasiewicz inequality proposed in [RB24].

Recently, optimization on the Riemannian manifold has provided new insights to the optimization community. In this regard, the manifold taken as the probability measure metric space equipped with the second-order Wasserstein distance is of particular interest, since optimization on it can be linked to practical sampling processes. In general, the oracle (continuous) optimization method on Wasserstein space is Riemannian gradient flow (i.e., Langevin dynamics when minimizing KL divergence). In this paper, we aim to enrich the continuous optimization methods in the Wasserstein space by extending the gradient flow into the stochastic gradient descent (SGD) flow and stochastic variance reduction gradient (SVRG) flow. The two flows on Euclidean space are standard stochastic optimization methods, while their Riemannian counterparts are not explored yet. By leveraging the structures in Wasserstein space, we construct a stochastic differential equation (SDE) to approximate the discrete dynamics of desired stochastic methods in the corresponded random vector space. Then, the flows of probability measures are naturally obtained by applying Fokker-Planck equation to such SDE. Furthermore, the convergence rates of the proposed Riemannian stochastic flows are proven, and they match the results in Euclidean space.

Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks. Motivated by the recent advances in fixed-time stability theory of continuous-time dynamical systems, we introduce a generalized framework for designing accelerated optimization algorithms with strongest convergence guarantees that further extend to a subclass of non-convex functions. In particular, we introduce the GenFlow algorithm and its momentum variant that provably converge to the optimal solution of objective functions satisfying the Polyak-{\L}ojasiewicz (PL) inequality in a fixed time. Moreover, for functions that admit non-degenerate saddle-points, we show that for the proposed GenFlow algorithm, the time required to evade these saddle-points is uniformly bounded for all initial conditions. Finally, for strongly convex-strongly concave minimax problems whose optimal solution is a saddle point, a similar scheme is shown to arrive at the optimal solution again in a fixed time. The superior convergence properties of our algorithm are validated experimentally on a variety of benchmark datasets.

We consider the momentum stochastic gradient descent scheme (MSGD) and its continuous-in-time counterpart in the context of non-convex optimization. We show almost sure exponential convergence of the objective function value for target functions that are Lipschitz continuous and satisfy the Polyak-Lojasiewicz inequality on the relevant domain, and under assumptions on the stochastic noise that are motivated by overparameterized supervised learning applications.