Pages that link to "Item:Q2425175"

The following pages link to First-order methods almost always avoid strict saddle points (Q2425175):

Displaying 20 items.

• The global optimization geometry of shallow linear neural networks (Q1988338) (← links)
• Regional complexity analysis of algorithms for nonconvex smooth optimization (Q2020615) (← links)
• Error bound of critical points and KL property of exponent 1/2 for squared F-norm regularized factorization (Q2052408) (← links)
• On the geometric analysis of a quartic-quadratic optimization problem under a spherical constraint (Q2089778) (← links)
• Triangularized orthogonalization-free method for solving extreme eigenvalue problems (Q2103436) (← links)
• On initial point selection of the steepest descent algorithm for general quadratic functions (Q2141353) (← links)
• Proximal methods avoid active strict saddles of weakly convex functions (Q2143222) (← links)
• Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions (Q2156337) (← links)
• A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions (Q2167333) (← links)
• Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance (Q2233558) (← links)
• An envelope for Davis-Yin splitting and strict saddle-point avoidance (Q2420798) (← links)
• Exploiting negative curvature in deterministic and stochastic optimization (Q2425164) (← links)
• Consensus-based optimization on hypersurfaces: Well-posedness and mean-field limit (Q3388781) (← links)
• Linear convergence of an alternating polar decomposition method for low rank orthogonal tensor approximations (Q6038672) (← links)
• Global convergence of the gradient method for functions definable in o-minimal structures (Q6052062) (← links)
• Convergence of the Momentum Method for Semialgebraic Functions with Locally Lipschitz Gradients (Q6071885) (← links)
• A geometric approach of gradient descent algorithms in linear neural networks (Q6099180) (← links)
• On the Global Convergence of Randomized Coordinate Gradient Descent for Nonconvex Optimization (Q6158001) (← links)
• Provable Phase Retrieval with Mirror Descent (Q6168333) (← links)
• Weighted Trace-Penalty Minimization for Full Configuration Interaction (Q6189167) (← links)