Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization

• URL: http://arxiv.org/abs/2605.29547v1
• Date: Thu, 28 May 2026 08:00:40 GMT
• Title: Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
• Abstract summary: We introduce Singularity-aware Adam (S-Adam), a novel that stabilizes training by dynamically modulating step sizes based on local geometric instability.<n>S-Adam incorporates an adaptive damping mechanism that decelerates updates in high-instability regions while preserving fast convergence in smooth basins.<n> Empirical evaluations on optimal Quantization-Aware Training (QAT) and high-noise small-batch learning demonstrate that S-Adam consistently outperforms AdamW and Prox-SGD.
• Score: 8.412194372218895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators. In such non-smooth regimes, adaptive optimizers such as Adam suffer from gradient chattering, violent oscillations caused by conflicting signals within the Clarke subdifferential, leading to poor convergence and suboptimal generalization. To address this, we introduce Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes training by dynamically modulating step sizes based on local geometric instability. Our key contribution is the Local Geometric Instability (LGI) metric, a computationally efficient estimator of the Clarke subdifferential diameter derived from the variance of randomized directional derivatives. S-Adam incorporates an adaptive damping mechanism exp(-$λ$$ρ$) that decelerates updates in high-instability regions while preserving fast convergence in smooth basins. We provide a rigorous convergence analysis using differential inclusions, proving that S-Adam converges almost surely to ($δ$,$ε$)-Clarke stationary points at the optimal O(1/$\sqrt(T)$) rate. Empirical evaluations on Quantization-Aware Training (QAT) and high-noise small-batch learning demonstrate that S-Adam consistently outperforms AdamW and Prox-SGD, achieving accuracy gains of up to 6 percent on CIFAR-100 and 3 percent on TinyImageNet while effectively mitigating gradient oscillations.

Related papers

• Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation [16.106678611834102]
  Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed noise.<n>Existing techniques typically rely on magnitude checks, which fail to distinguish informative geometric signals from outliers.
  arXiv  Detail & Related papers  (2026-06-21T10:57:37Z)
• Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization [11.723535704837266]
  Zeroth-Order (ZO) optimization is pivotal for scenarios where backpropagation is unavailable.<n>Existing methods face a stark trade-off: they are sample-inefficient (e.g., standard finite differences) or suffer from high variance due to randomized estimation.<n>In this work, we propose Coherent Coordinate Descent (CoCD), a deterministic, sample-efficient, and budget-aware ZO.
  arXiv  Detail & Related papers  (2026-05-14T04:52:24Z)
• Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling [43.822941944402544]
  Zeroth-Order optimization presents a promising memory-efficient paradigm for fine-tuning Large Language Models.<n>However, its practical adoption is severely constrained by slow wall-clock convergence and high estimation variance.<n>We propose AdaLeZO, an Adaptive Layer-wise ZO optimization framework.
  arXiv  Detail & Related papers  (2026-04-20T13:37:31Z)
• Causal Direction from Convergence Time: Faster Training in the True Causal Direction [0.0]
  We introduce Causal Computational Asymmetry (CCA), a principle for causal direction identification based on optimization dynamics.<n>CCA operates in optimization-time space, distinguishing it from methods such as RESIT, IGCI, and SkewScore.<n>We further embed CCA into a broader framework termed Causal Compression Learning (CCL), which integrates graph structure learning, causal information compression, and policy optimization.
  arXiv  Detail & Related papers  (2026-02-24T21:34:57Z)
• Revisiting the Initial Steps in Adaptive Gradient Descent Optimization [6.468625143772815]
  Adaptive gradient optimization methods, such as Adam, are prevalent in training deep neural networks across diverse machine learning tasks.<n>These methods often suffer from suboptimal generalization compared to descent gradient (SGD) and exhibit instability.<n>We introduce simple yet effective solutions: initializing the second-order moment estimation with non-zero values.
  arXiv  Detail & Related papers  (2024-12-03T04:28:14Z)
• Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise [60.92029979853314]
  We investigate the roles of gradient normalization and clipping in ensuring the convergence of Gradient Descent (SGD) under heavy-tailed noise. Our work provides the first theoretical evidence demonstrating the benefits of gradient normalization in SGD under heavy-tailed noise. We introduce an accelerated SGD variant incorporating gradient normalization and clipping, further enhancing convergence rates under heavy-tailed noise.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)
• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction [26.9632099249085]
  We propose two new variants of SPS and SLS, called AdaSPS and AdaSLS, which guarantee convergence in non-interpolation settings. We equip AdaSPS and AdaSLS with a novel variance reduction technique and obtain algorithms that require $smashwidetildemathcalO(n+1/epsilon)$ gradient evaluations.
  arXiv  Detail & Related papers  (2023-08-11T10:17:29Z)
• Convergence of Adam Under Relaxed Assumptions [72.24779199744954]
  We show that Adam converges to $epsilon$-stationary points with $O(epsilon-4)$ gradient complexity under far more realistic conditions. We also propose a variance-reduced version of Adam with an accelerated gradient complexity of $O(epsilon-3)$.
  arXiv  Detail & Related papers  (2023-04-27T06:27:37Z)
• Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator [75.05106948314956]
  We show that an increasing large momentum parameter for the first-order moment is sufficient for adaptive scaling.<n>We also give insights for increasing the momentum in a stagewise manner in accordance with stagewise decreasing step size.
  arXiv  Detail & Related papers  (2021-04-30T08:50:24Z)
• Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems [120.21685755278509]
  In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster in time up to an error. Rather than fixing the minibatch the step-size at the outset, we propose to allow parameters to evolve adaptively.
  arXiv  Detail & Related papers  (2020-07-02T16:02:02Z)
• MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients [112.00379151834242]
  We propose adaptive learning rate principle, in which the running mean of squared gradient in Adam is replaced by a weighted mean, with weights chosen to maximize the estimated variance each coordinate. This results in faster adaptation, which leads more desirable empirical convergence behaviors.
  arXiv  Detail & Related papers  (2020-06-21T21:47:43Z)
• Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets [71.05306664267832]
  Adaptive algorithms perform gradient updates using the history of gradients and are ubiquitous in training deep neural networks. In this paper we analyze a variant of OptimisticOA algorithm for nonconcave minmax problems. Our experiments show that adaptive GAN non-adaptive gradient algorithms can be observed empirically.
  arXiv  Detail & Related papers  (2019-12-26T22:10:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.