No article text was recorded for this version.
Hessian computation bottleneck
Version 1 of 128 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Preconditioner for A Primal-Dual Newton Conjugate Gradient Method for Compressed Sensing Problems
- Blog: Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study
- Blog: On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
- Blog: Stochastic Optimization for Nonconvex Problem With Inexact Hessian Matrix, Gradient, and Function
- Blog: Black Box Submodular Maximization: Discrete and Continuous Settings
- Blog: Using negative curvature in solving nonlinear programs
- Blog: Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization
- Blog: Inexact Newton-CG algorithms with complexity guarantees
- Blog: SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization
- Blog: Sub-sampled Cubic Regularization for Non-convex Optimization
- Blog: Estimating the Error of Randomized Newton Methods: A Bootstrap Approach
- Blog: RFN: A Random-Feature Based Newton Method for Empirical Risk Minimization in Reproducing Kernel Hilbert Spaces
- Blog: Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
- Blog: Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack
- Blog: Sub-sampled Newton Methods with Non-uniform Sampling
- Blog: Newton-Type Methods for Inference in Higher-Order Markov Random Fields
- Blog: Regularized stochastic BFGS algorithm
- Blog: Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality
- Blog: Variational Wasserstein Clustering
- Blog: Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion
- Blog: Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update
- Blog: A globally convergent incremental Newton method
- Blog: RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
- Blog: User-Device Authentication in Mobile Banking using APHEN for Paratuck2 Tensor Decomposition
- Blog: Correction: Limited-Memory Fast Gradient Descent Method for Graph Regularized Nonnegative Matrix Factorization
- Blog: RTRMC: A Riemannian trust-region method for low-rank matrix completion
- Blog: Sketch-and-Project Meets Newton Method: \\ Global $\mathcal O \left( k^{-2} \right)$ Convergence with Low-Rank Updates
- Blog: Utilizing Second Order Information in Minibatch Stochastic Variance Reduced Proximal Iterations
History & citation
Current · Permanent link
- This direction split from Scalable Second-Order Optimization for Neural Networks (82% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_hessian_computation_bottleneck_4904f41a,
title = {Hessian computation bottleneck},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hessian-computation-bottleneck/rdr_4904f41a527845bca539434fb827a220},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_hessian_computation_bottleneck_4904f41a_v1,
title = {Hessian computation bottleneck},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hessian-computation-bottleneck/rdr_4904f41a527845bca539434fb827a220/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}