No article text was recorded for this version.
step-size sensitivity
Version 1 of 1113 papers114 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
- Blog: Stochastic Approximation with Biased MCMC for Expectation Maximization
- Blog: GloptiNets: Scalable Non-Convex Optimization with Certificates
- Blog: Macrocanonical Models for Texture Synthesis
- Blog: Weighted SGD for $\ell_p$ Regression with Randomized Preconditioning
- Blog: Statistical inference with implicit SGD: proximal Robbins-Monro vs. Polyak-Ruppert
- Blog: Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization
- Blog: AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods
- Blog: Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity
- Blog: A Linearly-Convergent Stochastic L-BFGS Algorithm
- Blog: Sampling-based inference for large linear models, with application to linearised Laplace
- Blog: Learning robust and high-precision quantum controls
- Blog: Stochastic Adaptive Gradient Descent Without Descent
- Blog: Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
- Blog: AdaGrad stepsizes: sharp convergence over nonconvex landscapes
- Blog: Linear Convergence of Adaptive Stochastic Gradient Descent
- Blog: A scalable trust-region algorithm with application to mixed-norm regression
- Blog: Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization
- Blog: On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
- Blog: A Survey on Prompt Tuning
- Blog: GENO - GENeric Optimization for Classical Machine Learning
- Blog: Stochastic Gradients for Large-Scale Tensor Decomposition
- Blog: Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM
- Blog: Gradient-based algorithms for multi-objective bi-level optimization
- Blog: Self-Tuned Mirror Descent Schemes for Smooth and Nonsmooth High-Dimensional Stochastic Optimization
- Blog: Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization
- Blog: Projection-embedded BYY learning algorithm for Gaussian mixture-based clustering
- Blog: "Reliable and scalable variational inference for nonparametric mixtures, topics, and sequences"
- Blog: Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
- Blog: Handling the Positive-Definite Constraint in the Bayesian Learning Rule
- Blog: Bayesian Attention Belief Networks
- Blog: Theoretical analysis of Adam using hyperparameters close to one without Lipschitz smoothness
- Blog: MSL: An Adaptive Momentem-based Stochastic Line-search Framework
- Blog: Accelerated, Optimal and Parallel: Some results on model-based stochastic optimization
- Blog: An interior-point stochastic approximation method and an L1-regularized delta rule
- Blog: Stochastic Gradient Descent for Gaussian Processes Done Right
- Blog: A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning
- Blog: Data-Efficient Policy Evaluation Through Behavior Policy Search
- Blog: Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
- Blog: A Subsampling Line-Search Method with Second-Order Results
- Blog: Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization
- Blog: Modeling simple structures and geometry for better stochastic optimization algorithms
- Blog: Sequential Sample Average Majorization-Minimization
- Blog: Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time
- Blog: Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations
- Blog: Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models
- Blog: EM algorithms for ICA
- Blog: Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
- Blog: The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium
- Blog: Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting
- Blog: Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches
- Blog: A Unified Theory of Stochastic Proximal Point Methods without Smoothness
- Blog: Variance Reduced Smoothed Functional REINFORCE Policy Gradient Algorithms
- Blog: An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
- Blog: Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
- Blog: Sample Average Approximation for Black-Box Variational Inference
- Blog: Towards Understanding the Generative Capability of Adversarially Robust Classifiers
- Blog: RAt: Injecting Implicit Bias for Text-To-Image Prompt Refinement Models
- Blog: Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering
- Blog: Minorization-Maximization for Learning Determinantal Point Processes
Showing 60 of 113 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_step_size_sensitivity_75922388,
title = {step-size sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/step-size-sensitivity/rdr_75922388754f4cd19b3106c6a53404ee},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_step_size_sensitivity_75922388_v1,
title = {step-size sensitivity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/step-size-sensitivity/rdr_75922388754f4cd19b3106c6a53404ee/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}