Results 21 to 30 of about 1,963,727 (308)
On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond [PDF]
Neural Information Processing Systems, 2022 The FedProx algorithm is a simple yet powerful distributed proximal point optimization method widely used for federated learning (FL) over heterogeneous data.
Xiao-Tong Yuan, P. Li
semanticscholar +1 more source
Some New Types of Convergence Definitions for Random Variable Sequences
International Journal of Analysis and Applications, 2022 In this paper, we introduce the concepts of invariant convergence in probability, statistically invariant convergence in probability, invariant convergence almost surely, invariant convergence in distribution and invariant convergence in Lp-norm for ...
Saadettin Aydın
doaj +1 more source
Lacunary ℐ-Invariant Convergence of Sequence of Sets in Intuitionistic Fuzzy Metric Spaces
Journal of Mathematics, 2021 The concepts of invariant convergence, invariant statistical convergence, lacunary invariant convergence, and lacunary invariant statistical convergence for set sequences were introduced by Pancaroğlu and Nuray (2013).
Mualla Birgül Huban
doaj +1 more source
RING++: Roto-Translation Invariant Gram for Global Localization on a Sparse Scan Map [PDF]
IEEE Transactions on robotics, 2022 Global localization plays a critical role in many robot applications. LiDAR-based global localization draws the community's focus with its robustness against illumination and seasonal changes.
Xuecheng Xu +7 more
semanticscholar +1 more source
Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [PDF]
International Conference on Machine Learning, 2022 Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence.
Zhengquan Luo +4 more
semanticscholar +1 more source
Machines, 2021 For mechanical compound fault, it is of great significance to employ the vibration signal of a single-channel compound fault to analyze and realize the separation of multiple fault sources, which is essentially the problem of single-channel blind source ...
Haodong Yuan, Nailong Wu, Xinyuan Chen
doaj +1 more source
The backward Euler-Maruyama method for invariant measures of stochastic differential equations with super-linear coefficients [PDF]
Applied Numerical Mathematics, 2022 The backward Euler-Maruyama (BEM) method is employed to approximate the invariant measure of stochastic differential equations, where both the drift and the diffusion coefficient are allowed to grow super-linearly.
W. Liu, X. Mao, Yuehui Wu
semanticscholar +1 more source
Convergence properties of end invariants [PDF]
Geometry & Topology, 2013 We prove a continuity property for ending invariants of convergent sequences of Kleinian surface groups. We also analyze the bounded curve sets of such groups and show that their projections to non-annular subsurfaces lie a bounded Hausdorff distance from geodesics joining the projections of the ending invariants.
Brock, Jeffrey F +3 more
openaire +3 more sources
Global Convergence of Policy Gradient Primal–Dual Methods for Risk-Constrained LQRs [PDF]
IEEE Transactions on Automatic Control, 2021 While the techniques in optimal control theory are often model-based, the policy optimization (PO) approach directly optimizes the performance metric of interest. Even though it has been an essential approach for reinforcement learning problems, there is
Feiran Zhao, Keyou You, T. Başar
semanticscholar +1 more source
Cubically Convergent Iterations for Invariant Subspace Computation [PDF]
SIAM Journal on Matrix Analysis and Applications, 2004 Summary: We propose a Newton-like iteration that evolves on the set of fixed dimensional subspaces of \(\mathbb R^n\) and converges locally cubically to the invariant subspaces of a symmetric matrix. This iteration is compared in terms of numerical cost and global behavior with three other methods that display the same property of cubic convergence ...
Absil, P-A +3 more
openaire +2 more sources