Просмотр новости
Найдите то, что Вас интересует
Спутники
РН
SpaceX
Роскосмос
NASA
СпутникиРНSpaceXРоскосмосNASA
Block majorization-minimization (BMM) is a simple iterative algorithm for nonconvex optimization that sequentially minimizes a majorizing surrogate of the objective function in each block coordinate while the other block coordinates are held fixed. We consider a family of BMM algorithms for minimizing nonsmooth nonconvex objectives, where each parameter block is constrained within a subset of a Riemannian manifold. We establish that this algorithm converges asymptotically to the set of stationary points, and attains an $\epsilon$-stationary point within $\widetilde{O}(\epsilon^{-2})$ iterations. In particular, the assumptions for our complexity results are completely Euclidean when the underlying manifold is a product of Euclidean or Stiefel manifolds, although our analysis makes explicit use of the Riemannian geometry. Our general analysis applies to a wide range of algorithms with Riemannian constraints: Riemannian MM, block projected gradient descent, Bures-JKO scheme for Wasserstein variational inference, optimistic likelihood estimation, geodesically constrained subspace tracking, robust PCA, and Riemannian CP-dictionary-learning. We experimentally validate that our algorithm converges faster than standard Euclidean algorithms applied to the Riemannian setting.
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective | 0 | 10.94 | 17-08-2026 |
| 2 | Statistical Learning Theory for Neural Operators | 0 | 10.21 | 17-08-2026 |
| 3 | A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization | 0 | 9.82 | 17-08-2026 |
| 4 | A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems | 0 | 13.11 | 17-08-2026 |
| 5 | A Single-Loop Stochastic Proximal Quasi-Newton Method for Large-Scale Nonsmooth Convex Optimization | 0 | 8 | 17-08-2026 |
| 6 | Near-optimal Delta-convex Estimation of Lipschitz Functions | 0 | 9.71 | 17-08-2026 |
| 7 | Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex Optimization | 0 | 8.78 | 17-08-2026 |
| 8 | The Sample Complexity of Parameter-Free Stochastic Convex Optimization | 0 | 5.7 | 17-08-2026 |
| 9 | Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent | 0 | 8.24 | 17-08-2026 |
| 10 | Kernel-based Distributed Learning | 0 | 7 | 17-08-2026 |