No article text was recorded for this version.
generalized smoothness
Version 2 of 2144 papers238 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Provable Adaptivity in Adam
- Blog: Why gradient clipping accelerates training: A theoretical justification\n for adaptivity
- Blog: Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity
- Blog: AdaGrad under Anisotropic Smoothness
- Blog: Provable Adaptivity of Adam under Non-uniform Smoothness
- Blog: Generalized Gradient Norm Clipping & Non-Euclidean (L0,L1)-Smoothness
- Blog: Provable Adaptivity of Adam under Non-uniform Smoothness
- Blog: Robustness to Unbounded Smoothness of Generalized SignSGD
- Blog: Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
- Blog: MGDA Converges under Generalized Smoothness, Provably
- Blog: Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
- Blog: Variance-reduced Clipping for Non-convex Optimization
- Blog: Convergence of Steepest Descent and Adam under Non-Uniform Smoothness
- Blog: Error Feedback for Muon and Friends
- Blog: Provable Adaptivity of Adam under Non-uniform Smoothness
- Blog: Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
- Blog: Large Batch Analysis for Adagrad Under Anisotropic Smoothness
- Blog: On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
- Blog: Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance
- Blog: From Muon to Gluon: Bridging Theory and Practice of LMO-based Optimizers for LLMs
- Blog: A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks
- Blog: On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
- Blog: Leveraging Non-uniformity in First-order Non-convex Optimization
- Blog: Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
- Blog: Robustness to Unbounded Smoothness of Generalized SignSGD
- Blog: Parameter-free Clipped Gradient Descent Meets Polyak
- Blog: Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
- Blog: Analysis of Gradient Clipping and Adaptive Scaling with a Relaxed Smoothness Condition
- Blog: Approximate bregman proximal gradient algorithm for relatively smooth nonconvex optimization
- Blog: Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions
- Blog: Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
- Blog: Linear Convergence Rate in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness
- Blog: Armijo Line-search Makes (Stochastic) Gradient Descent Go Fast
- Blog: Delving into the Convergence of Generalized Smooth Minimax Optimization
- Blog: Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
- Blog: Revisiting Convergence of AdaGrad with Relaxed Assumptions
- Blog: Understanding Gradient Clipping In Incremental Gradient Methods
- Blog: Variance-reduced Clipping for Non-convex Optimization
- Blog: Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
- Blog: A New First-Order Meta-Learning Algorithm with Convergence Guarantees
- Blog: Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions
- Blog: Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
- Blog: SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
- Blog: On the Convergence of Multi-objective Optimization under Generalized Smoothness
- Blog: Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
- Blog: MGDA Converges under Generalized Smoothness, Provably
- Blog: Better LMO-based Momentum Methods with Second-Order Information
- Blog: On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond
- Blog: Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD
- Blog: Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
- Blog: Mirror Descent Under Generalized Smoothness
- Blog: Trust Region Methods for Nonconvex Stochastic Optimization beyond Lipschitz Smoothness
- Blog: Optimizing (L0, L1)-Smooth Functions by Gradient Methods
- Blog: Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization
- Blog: Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization
- Blog: On the Interaction of Noise, Compression Role, and Adaptivity under (L0, L1)-Smoothness: An SDE-based Approach
- Blog: Improved Analysis of Clipping Algorithms for Non-convex Optimization
- Blog: Algorithmic Foundation of Federated Learning with Sequential Data
- Blog: Why Do We Need Warm-up? A Theoretical Perspective
- Blog: Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
Showing 60 of 144 papers.
History & citation
Current · Permanent link
- Nonlinear Preconditioning for Generalized Smoothness merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_generalized_smoothness_ba7223a7,
title = {generalized smoothness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/generalized-smoothness/rdr_ba7223a7e83747b2b21dc85cffd91a5b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_generalized_smoothness_ba7223a7_v2,
title = {generalized smoothness},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/generalized-smoothness/rdr_ba7223a7e83747b2b21dc85cffd91a5b/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}