No article text was recorded for this version.
stochastic saddle point escape
Version 2 of 2524 papers770 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Second-Order Guarantees in Federated Learning
- Blog: Distributed Learning in Non-Convex Environments - Part II: Polynomial Escape from Saddle-Points
- Blog: Distributed Learning in Non-Convex Environments— Part II: Polynomial Escape From Saddle-Points
- Blog: On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
- Blog: Second-Order Guarantees of Stochastic Gradient Descent in Nonconvex Optimization
- Blog: Are good local minima wide in sparse recovery?
- Blog: Escaping Saddle Point Efficiently in Minimax and Bilevel Optimizations
- Blog: Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
- Blog: Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization
- Blog: Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
- Blog: Maximum Mean Discrepancy Gradient Flow
- Blog: Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape
- Blog: WITCHcraft: Efficient PGD attacks with random step size
- Blog: Perturbed Proximal Descent to Escape Saddle Points for Non-convex and Non-smooth Objective Functions
- Blog: Escaping Saddle Points with Compressed SGD
- Blog: PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization
- Blog: Stochastic Approximation for Online Tensorial Independent Component Analysis
- Blog: SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points
- Blog: Escaping from saddle points on Riemannian manifolds
- Blog: Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition
- Blog: Provable Compressed Sensing with Generative Priors via Langevin Dynamics
- Blog: On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
- Blog: Matrix Factorization in Tropical and Mixed Tropical-Linear Algebras
- Blog: Perturbed Proximal Descent to Escape Saddle Points for Non-convex and Non-smooth Objective Functions
- Blog: Distributed Gradient Methods for Nonconvex Optimization: Local and\n Global Convergence Guarantees
- Blog: Diffusion Approximations for Online Principal Component Estimation and Global Convergence
- Blog: Linear Speedup in Saddle-Point Escape for Decentralized Non-Convex Optimization
- Blog: Escaping Saddle Points for Zeroth-order Nonconvex Optimization using Estimated Gradient Descent
- Blog: SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points
- Blog: Escaping Saddle Points for Zeroth-order Non-convex Optimization using Estimated Gradient Descent
- Blog: Randomized coordinate gradient descent almost surely escapes strict saddle points
- Blog: Probable convexity and its application to Correlated Topic Models
- Blog: On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
- Blog: Escaping Saddles with Stochastic Gradients
- Blog: Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
- Blog: Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
- Blog: SGLB: Stochastic Gradient Langevin Boosting
- Blog: Implicit Regularization of Infinitesimally-perturbed Gradient Descent Toward Low-dimensional Solutions
- Blog: A deterministic gradient-based approach to avoid saddle points
- Blog: Diffusion Approximations for the Constant Learning Rate Backpropagation Algorithm and Resistence to Local Minima
- Blog: A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution
- Blog: Online Multiview Representation Learning: Dropping Convexity for Better Efficiency
- Blog: Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy
- Blog: Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms
- Blog: StochasticRank: Global Optimization of Scale-Free Discrete Functions
- Blog: Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent
- Blog: Stochastic Gradient Langevin Dynamics Algorithms with Adaptive Drifts
- Blog: On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
- Blog: Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
- Blog: Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition
- Blog: To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout
- Blog: Dynamic of Stochastic Gradient Descent with State-Dependent Noise
- Blog: On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
- Blog: Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization
- Blog: Faster Perturbed Stochastic Gradient Methods for Finding Local Minima
- Blog: Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization
- Blog: Microscopic Advances with Large-Scale Learning: Stochastic Optimization for Cryo-EM
- Blog: Escaping Saddles with Stochastic Gradients
- Blog: Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression
- Blog: Escaping Saddle Points with Adaptive Gradient Methods
Showing 60 of 524 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_stochastic_saddle_point_escape_89e06b56,
title = {stochastic saddle point escape},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/stochastic-saddle-point-escape/rdr_89e06b56274a4ce79fd47563ab8cec8e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_stochastic_saddle_point_escape_89e06b56_v2,
title = {stochastic saddle point escape},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/stochastic-saddle-point-escape/rdr_89e06b56274a4ce79fd47563ab8cec8e/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}