No article text was recorded for this version.
line search computational overhead
Version 1 of 173 papers75 conceptsfrozen 2026-10-04
Papers in this version
- Blog: No learning rates needed: Introducing SALSA - Stable Armijo Line Search Adaptation
- Blog: A new subspace minimization conjugate gradient method for unconstrained minimization
- Blog: Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields
- Blog: An Accelerated Proximal Gradient Algorithm for Singly Linearly Constrained Quadratic Programs with Box Constraints
- Blog: Golden Ratio Primal-Dual Algorithm with Linesearch
- Blog: Stochastic Sign Descent Methods: New Algorithms and Better Theory
- Blog: DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization
- Blog: An Enhanced Levenberg-Marquardt Method via Gram Reduction
- Blog: Adaptive Proximal Gradient Method for Convex Optimization
- Blog: Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
- Blog: Don't Be So Positive: Negative Step Sizes in Second-Order Methods
- Blog: Composite Convex Minimization Involving Self-concordant-Like Cost Functions
- Blog: Linearly Convergent Frank-Wolfe without Line-Search
- Blog: Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
- Blog: A Matrix Splitting Method for Composite Function Minimization
- Blog: Majorization-Minimization for Manifold Embedding
- Blog: Algorithmic Acceleration of Parallel ALS for Collaborative Filtering: Speeding up Distributed Big Data Recommendation in Spark
- Blog: Adaptive backtracking line search
- Blog: Randomness and permutations in coordinate descent methods
- Blog: A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions
- Blog: BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization
- Blog: Relationship between Batch Size and Number of Steps Needed for Nonconvex Optimization of Stochastic Gradient Descent using Armijo-Line-Search Learning Rate
- Blog: Hybrid Riemannian Conjugate Gradient Methods with Global Convergence Properties
- Blog: Handling the Positive-Definite Constraint in the Bayesian Learning Rule
- Blog: Empirical risk minimization: probabilistic complexity and stepsize strategy
- Blog: Inexact Newton-CG algorithms with complexity guarantees
- Blog: GLOBAL CONVERGENCE RESULTS OF A NEW THREE-TERM MEMORY GRADIENT METHOD
- Blog: Iterative Soft/Hard Thresholding With Homotopy Continuation for Sparse Recovery
- Blog: A first-order primal-dual method with adaptivity to local smoothness
- Blog: A Study on Trust Region Update Rules in Newton Methods for Large-scale Linear Classification
- Blog: Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
- Blog: Improving Line Search Methods for Large Scale Neural Network Training
- Blog: Adaptive Gradient Descent without Descent
- Blog: The backtrack Hölder gradient method with application to min-max and min-min problems
- Blog: Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
- Blog: The First Optimal Acceleration of High-Order Methods in Smooth Convex Optimization
- Blog: Composite Self-Concordant Minimization
- Blog: Accelerated Sparse Recovery via Gradient Descent with Nonlinear Conjugate Gradient Momentum
- Blog: Parallel Coordinate Descent Newton Method for Efficient L1 -Regularized Loss Minimization
- Blog: Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization
- Blog: A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions.
- Blog: Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
- Blog: Barzilai-Borwein Step Size for Stochastic Gradient Descent
- Blog: Linesearch-free adaptive Bregman proximal gradient for convex minimization without relative smoothness
- Blog: Extragradient Method in Optimization: Convergence and Complexity
- Blog: Glocal Smoothness: Line Search can really help!
- Blog: Faking Interpolation Until You Make It
- Blog: Optimal and Adaptive Monteiro-Svaiter Acceleration
- Blog: The Variable Metric Forward-Backward Splitting Algorithm Under Mild Differentiability Assumptions
- Blog: Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
- Blog: Revisiting Projection-Free Optimization for Strongly Convex Constraint Sets
- Blog: Greedy Newton: Newton's Method with Exact Line Search
- Blog: Randomized Block Frank-Wolfe for Convergent Large-Scale Learning
- Blog: On the convergence of adaptive first order methods: proximal gradient and alternating minimization algorithms
- Blog: Large-scale L-BFGS using MapReduce
- Blog: Toward a Unified Theory of Gradient Descent under Generalized Smoothness
- Blog: Adaptive gradient descent without descent
- Blog: Adaptive Coordinate-Wise Step Sizes for Quasi-Newton Methods: A Learning-to-Optimize Approach
- Blog: Adaptive Proximal Gradient Methods Are Universal Without Approximation
- Blog: Local search for multiobjective function optimization: pareto descent method
Showing 60 of 73 papers.
History & citation
Current · Permanent link
- This direction split from Linesearch Free Adaptive Optimization (96% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_line_search_computational_overhead_adf0dff2,
title = {line search computational overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/line-search-computational-overhead/rdr_adf0dff2923a42a1b49de0126b16550f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_line_search_computational_overhead_adf0dff2_v1,
title = {line search computational overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/line-search-computational-overhead/rdr_adf0dff2923a42a1b49de0126b16550f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}