# AdaGrad under Anisotropic Smoothness

arXiv: https://arxiv.org/abs/2406.15244 · HTML: https://mlsanity.com/paper/2406.15244/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 92 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Builds on (most cited first, 30 of 62)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [signSGD: Compressed Optimisation for Non-Convex Problems](https://mlsanity.com/paper/1802.04434/) (2018)
- [Large Batch Training of Convolutional Networks](https://mlsanity.com/paper/1708.03888/) (2017)
- [Online Learning: A Modern Introduction Using Convex Optimization](https://mlsanity.com/paper/1912.13213/) (2019)
- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training](https://mlsanity.com/paper/2305.14342/) (2023)
- [A Survey on Distributed Machine Learning](https://mlsanity.com/paper/1912.09789/) (2019)
- [AdaGrad stepsizes: Sharp convergence over nonconvex landscapes](https://mlsanity.com/paper/1806.01811/) (2018)
- [A Simple Convergence Proof of Adam and Adagrad](https://mlsanity.com/paper/2003.02395/) (2020)
- [Handbook of Convergence Theorems for (Stochastic) Gradient Methods](https://mlsanity.com/paper/2301.11235/) (2023)
- [Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond](https://mlsanity.com/paper/1611.07476/) (2016)
- [On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes](https://mlsanity.com/paper/1805.08114/) (2018)
- [Understanding Gradient Clipping in Private SGD: A Geometric Perspective](https://mlsanity.com/paper/2006.15429/) (2020)
- [Katyusha: The First Direct Acceleration of Stochastic Gradient Methods](https://mlsanity.com/paper/1603.05953/) (2016)
- [Why Transformers Need Adam: A Hessian Perspective](https://mlsanity.com/paper/2402.16788/) (2024)
- [Adam Can Converge Without Any Modification On Update Rules](https://mlsanity.com/paper/2208.09632/) (2022)
- [Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be](https://mlsanity.com/paper/2304.13960/) (2023)
- [Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping](https://mlsanity.com/paper/2005.10785/) (2020)
- [On Empirical Comparisons of Optimizers for Deep Learning](https://mlsanity.com/paper/1910.05446/) (2019)
- [Convergence of Adam Under Relaxed Assumptions](https://mlsanity.com/paper/2304.13972/) (2023)
- [Improved Analysis of Clipping Algorithms for Non-convex Optimization](https://mlsanity.com/paper/2010.02519/) (2020)
- [Scale-Free Online Learning](https://mlsanity.com/paper/1601.01974/) (2016)
- [Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees](https://mlsanity.com/paper/2305.01588/) (2023)

## Built on by (most cited first, 22 of 22)

- [Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)](https://mlsanity.com/paper/2505.13416/) (2025)
- [ASGO: Adaptive Structured Gradient Optimization](https://mlsanity.com/paper/2503.20762/) (2025)
- [Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf's Law](https://mlsanity.com/paper/2505.19227/) (2025)
- [Adam Exploits ℓ_∞-geometry of Loss Landscape via Coordinate-wise Adaptivity](https://mlsanity.com/paper/2410.08198/) (2024)
- [SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration](https://mlsanity.com/paper/2506.23803/) (2025)
- [On the O(frac√dK1/4) Convergence Rate of AdamW Measured by ℓ1 Norm](https://mlsanity.com/paper/2505.11840/) (2025)
- [Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates](https://mlsanity.com/paper/2511.11466/) (2025)
- [Unbiased Gradient Low-Rank Projection](https://mlsanity.com/paper/2510.17802/) (2025)
- [Better Convergence Guarantees for Sign-Based Momentum Methods](https://mlsanity.com/paper/2507.12091/) (2025)
- [Provable Benefit of SignGD: A Minimal Model Under Heavy-Tailed Class Imbalance](https://mlsanity.com/paper/2512.00763/) (2025)
- [StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models](https://mlsanity.com/paper/2604.15416/) (2026)
- [Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less](https://mlsanity.com/paper/2605.06654/) (2026)
- [Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence](https://mlsanity.com/paper/2509.07972/) (2025)
- [How do simple rotations affect the implicit bias of Adam?](https://mlsanity.com/paper/2510.23804/) (2025)
- [Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad](https://mlsanity.com/paper/2605.18694/) (2026)
- [Tight Complexity of Muon under Heavy-Tailed Noise](https://mlsanity.com/paper/2605.18528/) (2026)
- [Optimal Projection-Free Adaptive SGD for Matrix Optimization](https://mlsanity.com/paper/2604.02505/) (2026)
- [Adam-SHANG: A Convergent Adam-Type Method for Stochastic Smooth Convex Optimization](https://mlsanity.com/paper/2605.12878/) (2026)
- [Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?](https://mlsanity.com/paper/2606.23676/) (2026)
- [A regret minimization approach to fixed-point iterations](https://mlsanity.com/paper/2509.21653/) (2025)
- [Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness](https://mlsanity.com/paper/2609.30276/) (2026)
- [Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds](https://mlsanity.com/paper/2609.32729/) (2026)

## Abstract (arXiv)

Adaptive gradient methods have been widely adopted in training large-scale deep neural networks, especially large foundation models. Despite the huge success in practice, their theoretical advantages over classical gradient methods with uniform step sizes across all coordinates (e.g. SGD) have not been fully understood, especially in the large batch-size setting commonly used in practice. This is because the only theoretical result that can demonstrate this benefit was obtained in the original paper of Adagrad for convex nonsmooth objective functions, which is insufficient for large batch algorithms. In this work, we attempt to resolve this gap between theory and practice by proposing a novel anisotropic generalized smoothness assumption and providing corresponding analyses of Adagrad. It is shown that under anisotropic smoothness and noise conditions, AdaGrad can achieve faster convergence guarantees in terms of better dimensional dependence than algorithms with uniform step sizes across all coordinates. Experiments in logistic regression and instruction following fine-tuning tasks provide strong evidence to support our novel assumption and theoretical analysis.