# Parameter-Agnostic Optimization under Relaxed Smoothness

arXiv: https://arxiv.org/abs/2311.03252 · HTML: https://mlsanity.com/paper/2311.03252/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 30 of 33)

- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [Lower Bounds for Non-Convex Stochastic Optimization](https://mlsanity.com/paper/1912.02365/) (2019)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [AdaGrad stepsizes: Sharp convergence over nonconvex landscapes](https://mlsanity.com/paper/1806.01811/) (2018)
- [Momentum Improves Normalized SGD](https://mlsanity.com/paper/2002.03305/) (2020)
- [Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence](https://mlsanity.com/paper/2002.10542/) (2020)
- [Coin Betting and Parameter-Free Online Learning](https://mlsanity.com/paper/1602.04128/) (2016)
- [Lower Bounds for Finding Stationary Points I](https://mlsanity.com/paper/1710.11606/) (2017)
- [Black-Box Reductions for Parameter-free Online Learning in Banach Spaces](https://mlsanity.com/paper/1802.06293/) (2018)
- [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)
- [Robustness to Unbounded Smoothness of Generalized SignSGD](https://mlsanity.com/paper/2208.11195/) (2022)
- [The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance](https://mlsanity.com/paper/2202.05791/) (2022)
- [Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies](https://mlsanity.com/paper/2302.01734/) (2023)
- [How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD](https://mlsanity.com/paper/1801.02982/) (2018)
- [Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions](https://mlsanity.com/paper/2305.18471/) (2023)
- [UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization](https://mlsanity.com/paper/1910.13857/) (2019)
- [Revisiting the Polyak step size](https://mlsanity.com/paper/1905.00313/) (2019)
- [Online Adaptive Methods, Universality and Acceleration](https://mlsanity.com/paper/1809.02864/) (2018)
- [Convex and Non-convex Optimization Under Generalized Smoothness](https://mlsanity.com/paper/2306.01264/) (2023)
- [Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD](https://mlsanity.com/paper/2302.06570/) (2023)
- [Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution](https://mlsanity.com/paper/2205.04583/) (2022)
- [Online Learning Without Prior Information](https://mlsanity.com/paper/1703.02629/) (2017)
- [The Complexity of Finding Stationary Points with Stochastic Gradient Descent](https://mlsanity.com/paper/1910.01845/) (2019)
- [Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods](https://mlsanity.com/paper/2305.12475/) (2023)
- [Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction](https://mlsanity.com/paper/2308.06058/) (2023)
- [Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent](https://mlsanity.com/paper/2110.11442/) (2021)

## Built on by (most cited first, 29 of 29)

- [Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)](https://mlsanity.com/paper/2505.13416/) (2025)
- [From Gradient Clipping to Normalization for Heavy Tailed SGD](https://mlsanity.com/paper/2410.13849/) (2024)
- [Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping](https://mlsanity.com/paper/2412.19529/) (2024)
- [Generalized Gradient Norm Clipping & Non-Euclidean (L0,L1)-Smoothness](https://mlsanity.com/paper/2506.01913/) (2025)
- [Can SGD Handle Heavy-Tailed Noise?](https://mlsanity.com/paper/2508.04860/) (2025)
- [On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond](https://mlsanity.com/paper/2403.15146/) (2024)
- [Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under (L0, L1)-Smoothness](https://mlsanity.com/paper/2502.07923/) (2025)
- [Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence](https://mlsanity.com/paper/2402.17722/) (2024)
- [Understanding Adam Requires Better Rotation Dependent Assumptions](https://mlsanity.com/paper/2410.19964/) (2024)
- [Loss Landscape Characterization of Neural Networks without Over-Parametrization](https://mlsanity.com/paper/2410.12455/) (2024)
- [Muon is Provably Faster with Momentum Variance Reduction](https://mlsanity.com/paper/2512.16598/) (2025)
- [Adaptive Gradient Normalization and Independent Sampling for (Stochastic) Generalized-Smooth Optimization](https://mlsanity.com/paper/2410.14054/) (2024)
- [Error Feedback under (L0,L1)-Smoothness: Normalization and Momentum](https://mlsanity.com/paper/2410.16871/) (2024)
- [On the Interaction of Batch Noise, Adaptivity, and Compression, under (L0,L1)-Smoothness: An SDE Approach](https://mlsanity.com/paper/2506.00181/) (2025)
- [Simple Convergence Proof of Adam From a Sign-like Descent Perspective](https://mlsanity.com/paper/2507.05966/) (2025)
- [Smoothed Normalization for Efficient Distributed Private Optimization](https://mlsanity.com/paper/2502.13482/) (2025)
- [Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster](https://mlsanity.com/paper/2503.00229/) (2025)
- [LightSAM: Parameter-Agnostic Sharpness-Aware Minimization](https://mlsanity.com/paper/2505.24399/) (2025)
- [Improved Convergence in Parameter-Agnostic Error Feedback through Momentum](https://mlsanity.com/paper/2511.14501/) (2025)
- [Why is Normalization Preferred? A Worst-Case Complexity Theory for Stochastically Preconditioned SGD under Heavy-Tailed Noise](https://mlsanity.com/paper/2602.13413/) (2026)
- [Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method](https://mlsanity.com/paper/2605.18174/) (2026)
- [Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success](https://mlsanity.com/paper/2606.14560/) (2026)
- [Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and (L0, L1)-Smoothness](https://mlsanity.com/paper/2508.06884/) (2025)
- [Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness](https://mlsanity.com/paper/2601.03566/) (2026)
- [Stability and Generalization of Stochastic Nonconvex Optimization under Heavy-Tailed Noise: From Gradient Norm to Goldstein Stationarity](https://mlsanity.com/paper/2601.19730/) (2026)
- [Byzantine-Robust Optimization under (L0, L1)-Smoothness](https://mlsanity.com/paper/2603.12512/) (2026)
- [Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness](https://mlsanity.com/paper/2609.30276/) (2026)
- [TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise](https://mlsanity.com/paper/2609.30732/) (2026)
- [Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization](https://mlsanity.com/paper/2610.01572/) (2026)

## Abstract (arXiv)

Tuning hyperparameters, such as the stepsize, presents a major challenge of training machine learning models. To address this challenge, numerous adaptive optimization algorithms have been developed that achieve near-optimal complexities, even when stepsizes are independent of problem-specific parameters, provided that the loss function is L-smooth. However, as the assumption is relaxed to the more realistic (L0, L1)-smoothness, all existing convergence results still necessitate tuning of the stepsize. In this study, we demonstrate that Normalized Stochastic Gradient Descent with Momentum (NSGD-M) can achieve a (nearly) rate-optimal complexity without prior knowledge of any problem parameter, though this comes at the cost of introducing an exponential term dependent on L1 in the complexity. We further establish that this exponential term is inevitable to such schemes by introducing a theoretical framework of lower bounds tailored explicitly for parameter-agnostic algorithms. Interestingly, in deterministic settings, the exponential factor can be neutralized by employing Gradient Descent with a Backtracking Line Search. To the best of our knowledge, these findings represent the first parameter-agnostic convergence results under the generalized smoothness condition. Our empirical experiments further confirm our theoretical insights.