- Referenced in 50 articles
- variable, then HOGWILD! achieves a nearly optimal rate of convergence. We demonstrate experimentally that HOGWILD...
- Referenced in 273 articles
- algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates ... rate that is comparable to the best known results under the online convex optimization framework...
- Referenced in 30 articles
- NeNMF: An optimal gradient method for non-negative matrix factorization. Nonnegative matrix factorization ... following three problems: slow convergence rate, numerical instability and nonconvergence. In this paper, we present ... time consuming line search and converges optimally at rate in optimizing each matrix factor ... manifold regularized NMF with the optimal convergence rate. Numerical experiments on both synthetic and real...
- Referenced in 53 articles
- ForWaRD’s MSE decays with the optimal WVD rate as the number of samples increases...
- Referenced in 36 articles
- handle large-scale sparse data. 2) Optimal Convergence Rate. The convergence rate O(1/k2...
- Referenced in 27 articles
- flexible, efficient and achieves the optimal rate of convergence. Several options and generalizations are included...
- Referenced in 21 articles
- considered: It is shown that optimal rates of convergence are obtained without the need ... Unity, it is possible to recover optimal convergence rates in the case of re-entrant...
- Referenced in 28 articles
- inertial term for solving a strongly convex optimization problem of a certain type. The strongly ... used for deriving a worst-case convergence rate for the proposed algorithm ... proved to be an optimal algorithm with linear rate of convergence. For certain problems this ... better than the provably optimal worst-case rate of convergence for smooth strongly convex functions...
- Referenced in 30 articles
- into the class zones and the optimized-learning-rate algorithm OLVQ1...
- Referenced in 197 articles
- maintenance, which we term automated empirical optimization of software; this style of library management ... software to keep pace with the incredible rate of hardware advancement inherent in Moore...
- Referenced in 80 articles
- encryption speed in software and hardware. An optimized implementation of Camellia in assembly language ... Pentium III (800 MHz) at the rate of more than 276 Mbits per second, which ... much faster than the speed of an optimized DES implementation. In addition, a distinguishing feature...
- Referenced in 260 articles
- problem of learning a ranking function. The optimization algorithms used in SVMlight are described ... efficient estimation methods for both error rate and precision/recall. XiAlpha-estimates [Joachims, 2002a, Joachims, 2000b ... algorithm proceeds by solving a sequence of optimization problems lower-bounding the solution using...
- Referenced in 224 articles
- algebra by exploring ratio and proportion, rate of change, and functional relationships through numeric, tabular ... trigonometric—promoting deep understanding. Sketchpad is the optimal tool for interactive whiteboards. Teachers...
- Referenced in 31 articles
- gradient method: Universal gradient methods for convex optimization problems. In this paper, we present ... class they automatically ensure the best possible rate of convergence. We confirm our theoretical results ... that the fast rate of convergence, typical for the smooth optimization problems, sometimes...
- Referenced in 9 articles
- fast to compute, achieves the optimal detection rate and estimates the number of change points...
- Referenced in 4 articles
- CHIME are investigated. We establish the optimal rate of convergence for the excess misclustering error ... show that CHIME is minimax rate optimal. In addition, the optimality of the proposed estimator...
- Referenced in 12 articles
- method, FDRSeg, which controls the false discovery rate (FDR) in the sense that the number ... uniform sense at optimal minimax convergence rates up to a log-factor. The latter...
- Referenced in 97 articles
- paradigm stems from recent advances in stochastic optimization and online learning which employ proximal functions ... function, which significantly simplifies setting a learning rate and results in regret guarantees that...
- Referenced in 39 articles
- Optimized Evidence-Theoretic K-Nearest Neighbor) classifiers. The success rates obtained by MemType...
- Referenced in 8 articles
- manufactured solutions are presented assuring optimal convergence rates of the approximations, showing the accuracy...