No article text was recorded for this version.
distance-based step size adaptation
Version 1 of 133 papers38 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Towards Simple and Provable Parameter-Free Adaptive Gradient Methods
- Blog: Learning-Rate-Free Learning by D-Adaptation
- Blog: Offline Model-Based Optimization via Policy-Guided Gradient Search
- Blog: DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
- Blog: Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
- Blog: Online Learning Without Prior Information
- Blog: The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance
- Blog: Linear Convergence of Adaptive Stochastic Gradient Descent
- Blog: A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise
- Blog: Layer-Specific Adaptive Learning Rates for Deep Networks
- Blog: Delving into the Convergence of Generalized Smooth Minimax Optimization
- Blog: Learning filter widths of spectral decompositions with wavelets
- Blog: Momentum-Based Variance Reduction in Non-Convex SGD
- Blog: SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance
- Blog: DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
- Blog: Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
- Blog: Continuous-Time Accelerated Methods via a Hybrid Control Lens
- Blog: Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
- Blog: Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates
- Blog: Online Learning-guided Learning Rate Adaptation via Gradient Alignment
- Blog: Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation
- Blog: Covisibility-Based Map Learning Method for Mobile Robots
- Blog: Prodigy: An Expeditiously Adaptive Parameter-Free Learner
- Blog: On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes
- Blog: Tuning-Free Stochastic Optimization
- Blog: Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis
- Blog: Adaptive Regret of Convex and Smooth Functions
- Blog: BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
- Blog: On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
- Blog: Dynamic Regret Reduces to Kernelized Static Regret
- Blog: Algorithms for Non-negative Matrix Factorization
- Blog: Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
- Blog: Improving Online-to-Nonconvex Conversion for Smooth Optimization via Double Optimism
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_distance_based_step_size_adaptation_7a1ca213,
title = {distance-based step size adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/distance-based-step-size-adaptation/rdr_7a1ca21310974fb2ae364755e49899ba},
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_distance_based_step_size_adaptation_7a1ca213_v1,
title = {distance-based step size adaptation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/distance-based-step-size-adaptation/rdr_7a1ca21310974fb2ae364755e49899ba/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}