Latest Research in Stochastic Gradient Optimization Techniques

Top Research Topics in Stochastic Gradient Optimization Techniques

• Optimization and Control — 10 papers
• Machine Learning — 4 papers
• Stochastic Gradient Optimization Techniques — 3 papers
• Machine Learning — 2 papers
• Statistics Theory — 2 papers
• Probability — 2 papers
• Signal Processing — 1 papers
• Soft Condensed Matter — 1 papers
• Differential Equations and Boundary Problems — 1 papers
• Information Theory — 1 papers

Highest-Cited Papers

1. On the Performance of Stochastic Gradient Methods with Momentum in Time-Varying Regimes
2. TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models
3. Stochastic optimization algorithms for problems with controllable biased oracles (1 citations)
4. Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles
5. Low Dimensional Sampling under Reconstructed Constraints
6. The anisotropic local law for sample covariance matrices under quadratic-form concentration
7. An Alternating Direction Method of Multipliers for Utility-based Shortfall Risk Portfolio Optimization
8. Learning-Based Surrogate Method for Stochastic Optimization under Decision-Dependent Uncertainty with Adaptive Random Designs
9. A Lower Bound for the Heavy-Ball Method on Smooth Convex Functions
10. A Subsampled Davis-Kahan Bound for Large-Scale Eigenspace Estimation
11. Stronger Lower Bounds for (Non-)Anytime Acceleration of Gradient Descent
12. An Adaptive Projected-Gradient Algorithm for Sample-Average Approximations of Stochastic Multi-Objective Optimization
13. Adaptive-batch stochastic gradient descent for constrained optimization based on relaxed barrier functions
14. The Symmetric Location Problem: a Song of (statistical) Efficiency and Robustness
15. New insights into the NLP-Id bound for maximum-entropy sampling
16. DOFFO_TR: a Decentralized Objective Function-Free Optimization method with Trust-Region
17. A GPU-accelerated Nonlinear Branch-and-Bound Framework for Sparse Linear Models
18. A dual network approach to connect structure and flow in random networks
19. An approximate zero bias transformation for random sums: Applications to sampling with outliers, auto insurance, and generative AI
20. Identifiability and exact reconstruction of the optimal transport cost on finite spaces