Latest Research in Gradient Descent Geometries

Top Research Topics in Gradient Descent Geometries

• Optimization and Control — 61 papers
• Machine Learning — 19 papers
• Statistics Theory — 16 papers
• Machine Learning — 10 papers
• Probability — 8 papers
• Stochastic Gradient Optimization Techniques — 7 papers
• Numerical Analysis — 7 papers
• Information Theory — 6 papers
• Computation — 5 papers
• Geometric Analysis and Curvature Flows — 4 papers

Highest-Cited Papers

1. On the Performance of Stochastic Gradient Methods with Momentum in Time-Varying Regimes
2. Kinetic interacting particle Langevin Monte Carlo
3. A Mathematical Theory of Pragmatic Information
4. TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models
5. Incremental Column Subset Selection via Conditional Determinantal Point Processes
6. Near-Optimal Pure Single-Loop Extragradient Method for Strongly Convex--Strongly Concave Minimax Optimization
7. A Regularized Newton-Type Method for Manifold--Affine Intersection Problems under Intrinsic Transversality
8. Geometry and Convergence of Quadratically Regularized Optimal Transport I
9. Optimal Network Dependence in Distributed Stochastic Optimization via Tree Routing
10. Stochastic optimization algorithms for problems with controllable biased oracles (1 citations)
11. Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Minimization Oracles
12. Spectral gap of Metropolis-within-Gibbs under log-concavity
13. Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization
14. Stochastic Optimization Algorithms for Problems with Controllable Biased Oracles
15. An operator splitting analysis of Wasserstein--Fisher--Rao gradient flows
16. Near-Optimal Deterministic Exact-Value Complexity for Smooth Convex Optimization
17. Curvature-aware Expected Free Energy as an Acquisition Function for Bayesian Optimization
18. Fast Learning Rates for Physics-Informed Kernel Methods
19. Algorithms for adaptive and heteroskedastic linear regression at the computational threshold
20. A Provably Exact Distributed ADMM Projection onto Graph-Constrained Doubly Stochastic Matrices (2 citations)

Sub-Regions

• Multi-Criteria Decision Making — 85 papers
• Optimization and Control — 81 papers
• Machine Learning — 31 papers
• Stochastic Gradient Optimization Techniques — 28 papers
• Geometric Analysis and Curvature Flows — 22 papers
• Statistics Theory — 22 papers