No article text was recorded for this version.
initialization robustness
Version 2 of 2157 papers163 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AdaGrad stepsizes: Sharp convergence over nonconvex landscapes, from any initialization
- Blog: A Parallel Graph Planarization Algorithm Using Gradient Ascent Learning of Hopfield Network.
- Blog: AdaLoss: A Computationally-Efficient and Provably Convergent Adaptive Gradient Method
- Blog: AdaLoss: A computationally-efficient and provably convergent adaptive gradient method
- Blog: Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
- Blog: A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
- Blog: Stochastic optimization under time drift: iterate averaging, step-decay schedules, and high probability guarantees
- Blog: Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds
- Blog: Convergence of adaptive algorithms for constrained weakly convex optimization
- Blog: Using Curvature Information for Fast Stochastic Search
- Blog: Adaptive Consensus ADMM for Distributed Optimization
- Blog: Learning-Rate-Free Learning by D-Adaptation
- Blog: Learning One Convolutional Layer with Overlapping Patches
- Blog: Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient
- Blog: Toward Communication Efficient Adaptive Gradient Method
- Blog: Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization
- Blog: Appropriate Learning Rates of Adaptive Learning Rate Optimization\n Algorithms for Training Deep Neural Networks
- Blog: An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning
- Blog: FedNAR: Federated Optimization with Normalized Annealing Regularization
- Blog: Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
- Blog: Optimal stochastic mirror descent methods for smooth, nonsmooth, and high-dimensional stochastic optimization
- Blog: Stochastic Adaptive Gradient Descent Without Descent
- Blog: Path Integral Policy Improvement with Covariance Matrix Adaptation
- Blog: Adaptive backtracking line search
- Blog: SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms
- Blog: Linear Convergence of Adaptive Stochastic Gradient Descent
- Blog: Autotuning Plug-and-Play Algorithms for MRI
- Blog: Discovering Evolution Strategies via Meta-Black-Box Optimization
- Blog: Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter
- Blog: MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent
- Blog: Metatrace: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control
- Blog: Adaptive ADMM with Spectral Penalty Parameter Selection
- Blog: Restarting Frank-Wolfe
- Blog: Grad-GradaGrad? A Non-Monotone Adaptive Stochastic Gradient Method
- Blog: Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms
- Blog: Smoothness-Adaptive Sharpness-Aware Minimization for Finding Flatter Minima
- Blog: Accelerating Level-Value Adjustment for the Polyak Stepsize
- Blog: CONGA:Confidence-and-Gradient-Aware Learning Rate Schedule for Test Time Adaptation
- Blog: BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization
- Blog: Probabilistic Line Searches for Stochastic Optimization
- Blog: SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
- Blog: Online hyperparameter optimization by real-time recurrent learning
- Blog: MoMo: Momentum Models for Adaptive Learning Rates
- Blog: Enhancing Language Model Alignment: A Confidence-Based Approach to Label Smoothing
- Blog: Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights
- Blog: Online Learning Rate Adaptation with Hypergradient Descent
- Blog: SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques
- Blog: Dataset Distillation by Automatic Training Trajectories
- Blog: KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
- Blog: Generalisable Agents for Neural Network Optimisation
- Blog: On ADMM in Deep Learning: Convergence and Saturation-Avoidance
- Blog: Parameter-Free FISTA by Adaptive Restart and Backtracking
- Blog: Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting
- Blog: AutoLoss: Learning Discrete Schedule for Alternate Optimization
- Blog: Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration
- Blog: A consensus-based global optimization method with adaptive momentum estimation
- Blog: An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds
- Blog: A Subsampling Line-Search Method with Second-Order Results
- Blog: Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers
- Blog: Pairwise Learning with Adaptive Online Gradient Descent
Showing 60 of 157 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_initialization_robustness_92c2a2ed,
title = {initialization robustness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/initialization-robustness/rdr_92c2a2edba7e4c22b5ad97f1c12905af},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_initialization_robustness_92c2a2ed_v2,
title = {initialization robustness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/initialization-robustness/rdr_92c2a2edba7e4c22b5ad97f1c12905af/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}