• # PESTO

• Referenced in 36 articles [sw20864]
• variants of fast proximal gradient, conditional gradient, subgradient and alternating projection methods. In particular ... worst-case guarantee for the conditional gradient method by more than a factor ... also show how the optimized gradient method proposed by Kim and Fessler ... fast as the standard accelerated proximal gradient method...

• Referenced in 166 articles [sw22202]
• present a new family of subgradient methods that dynamically incorporate knowledge of the geometry ... earlier iterations to perform more informative gradient-based learning. Metaphorically, the adaptation allows ... stochastic optimization and online learning which employ proximal functions to control the gradient steps ... analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning...
• # Saga

• Referenced in 104 articles [sw39677]
• this work we introduce a new optimisation method called SAGA in the spirit ... SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA ... support for composite objectives where a proximal operator is used on the regulariser. Unlike SDCA ... experimental results showing the effectiveness of our method...
• # 2EBD-HPE

• Referenced in 15 articles [sw31879]
• Block-Decomposition (BD) method based on the BD-hybrid proximal extra-gradient. The main contribution ... gradient step and then they use a scaling factor to balance the blocks. The method...
• # SLEP

• Referenced in 42 articles [sw13487]
• evaluate the function value and the gradient; and thus the algorithms can handle large-scale ... order black-box methods. 3) Efficient Projection. The projection problem (proximal operator) can be solved...
• # iPiano

• Referenced in 68 articles [sw09623]
• iPiano: inertial proximal algorithm for nonconvex optimization. In this paper we study an algorithm ... nonsmooth split version of the Heavy-ball method from Polyak. A rigorous analysis ... used to prove convergence for several other gradient methods. First, an abstract convergence theorem...
• # PredictPDPS.jl

• Referenced in 1 article [sw39172]
• corresponding predictive online primal-dual proximal splitting method. The video frames now exactly correspond ... based on (proximal) gradient flow. This affects the model that the method asymptotically minimises...
• # MDC-ELLIPSOIDs

• Referenced in 11 articles [sw22577]
• linear equations with the Newton-Raphson method with analytical Jacobians. The system of non-linear ... vector calculus, is derived as the gradient of the implicit function. The Householder transformation ... them is collinear to the surface normal. Proximity queries were also implemented to test ... separate condition) contact detection. Note that the proximity queries do not calculate the minimum distance...
• # ProxSARAH

• Referenced in 9 articles [sw35438]
• proximal gradient and an averaging step making them different from existing nonconvex proximal-type algorithms ... order oracle. One key step of our methods is the new constant and dynamic step...
• # RMTL

• Referenced in 1 article [sw41670]
• network incorporation. Based on the accelerated gradient descent method, the algorithms feature a state ... structure is induced by the solving the proximal operator. The detail of the package...
• # NPPC

• Referenced in 4 articles [sw08728]
• cost. NPPC classifies binary patterns by the proximity ... constraints and solved it by Newton’s method and the solution is updated by solving ... system of linear equations by conjugate gradient method. The performance of the reformulated NPPC...
• # FarRSA

• Referenced in 1 article [sw25237]
• norm regularizer. The main features of the method include: (i) an evolving set of indices ... subproblem must be solved, which allow conjugate gradient or coordinate descent techniques to be employed ... updated; and (v) a reduced proximal gradient step that ensures a sufficient decrease ... expanded. We prove global convergence of the method and demonstrate its performance...
• # ProMP

• Referenced in 2 articles [sw34914]
• ProMP: Proximal Meta-Policy Search. Credit assignment in Meta-reinforcement learning (Meta-RL) is still ... poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement ... theoretical analysis of credit assignment in gradient-based Meta-RL. Building on the gained insights...
• # Inertial-SsGM

• Referenced in 1 article [sw42307]
• Delayed Derivatives for Nonconvex Problems. Stochastic gradient methods (SGMs) are predominant approaches for solving stochastic ... certain acceleration technique to a stochastic subgradient method (SsGM) for nonsmooth nonconvex problems. In addition ... inertial proximal SsGM for solving nonsmooth nonconvex stochastic optimization problems. The proposed method can have ... expected value of the gradient norm square, for $K$ iterations. In a distributed environment...
• # DiffPills

• Referenced in 0 articles [sw42464]
• learning for robotic systems. However, no existing method is differentiable with respect to the configurations ... resulting algorithms are able to return a proximity value indicating if a collision has taken ... used reliably within other gradient-based optimization methods, including trajectory optimization, state estimation, and reinforcement...