VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence

• URL: http://arxiv.org/abs/2505.13954v2
• Date: Mon, 29 Sep 2025 07:30:09 GMT
• Title: VAMO: Efficient Zeroth-Order Variance Reduction for SGD with Faster Convergence
• Authors: Jiahe Chen, Ziye Ma,
• Abstract summary: Large-scale non problems are common in deep learning.<n>First-order (FO)s serve as today's baselines.<n>ZO algorithms reduce the size of computation and memory costs.<n>VAMO achieves these gains with smaller dynamic memory requirements.
• Score: 6.574641780732972
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimizing large-scale nonconvex problems, common in deep learning, demands balancing rapid convergence with computational efficiency. First-order (FO) optimizers, which serve as today's baselines, provide fast convergence and good generalization but often incur high computation and memory costs due to the large size of modern models. Conversely, zeroth-order (ZO) algorithms reduce this burden using estimated gradients, yet their slow convergence in high-dimensional settings limits practicality. We introduce VAMO (VAriance-reduced Mixed-gradient Optimizer), a stochastic variance-reduced method that extends mini-batch SGD with full-batch ZO gradients under an SVRG-style framework. VAMO's hybrid design utilizes a two-point ZO estimator to achieve a dimension-agnostic convergence rate of $\mathcal{O}(1/T + 1/b)$, where $T$ is the number of iterations and $b$ is the batch-size, surpassing the dimension-dependent slowdown of purely ZO methods and significantly improving over SGD's $\mathcal{O}(1/\sqrt{T})$ rate. Additionally, we propose a multi-point variant that mitigates the $O(1/b)$ error by adjusting the number of estimation points to balance convergence and cost. Importantly, VAMO achieves these gains with smaller dynamic memory requirements than many FO baselines, making it particularly attractive for edge deployment. Experiments including traditional neural network training and LLM finetuning confirm that VAMO not only outperforms established FO and ZO methods, but also does so with a light memory footprint.

Related papers

• Evolution Strategies at the Hyperscale [57.75314521465674]
  We introduce EGGROLL, an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes.<n>ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives.<n>EGGROLL overcomes these bottlenecks by generating random matrices $Ain mathbbRmtimes r, Bin mathbbRntimes r$ with $rll min(m,n)$ to form a low-rank matrix perturbation $A Btop$
  arXiv  Detail & Related papers  (2025-11-20T18:56:05Z)
• A Trainable Optimizer [18.195022468462753]
  We present a framework that jointly trains the full gradient estimator and the trainable weights of the model.<n>Pseudo-linear TO incurs negligible computational overhead, requiring only minimal additional multiplications.<n> Experiments demonstrate that TO methods converge faster than benchmark algorithms.
  arXiv  Detail & Related papers  (2025-08-03T14:06:07Z)
• Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order [39.25335214877435]
  Fine-tuning Large Language Models (LLMs) is essential for adapting pre-trained models to downstream tasks.<n>Traditional first-order algorithms incur prohibitive memory and computational costs that scale poorly with model size.<n>We propose zero-order (ZO) optimization methods as a memory- and compute-efficient alternative.
  arXiv  Detail & Related papers  (2025-06-04T20:27:17Z)
• Second-order Optimization of Gaussian Splats with Importance Sampling [51.95046424364725]
  3D Gaussian Splatting (3DGS) is widely used for novel view rendering due to its high quality and fast inference time.<n>We propose a novel second-order optimization strategy based on Levenberg-Marquardt (LM) and Conjugate Gradient (CG)<n>Our method achieves a $3times$ speedup over standard LM and outperforms Adam by $6times$ when the Gaussian count is low.
  arXiv  Detail & Related papers  (2025-04-17T12:52:08Z)
• SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning [18.055120576191204]
  Ill-conditioned objectives and nonsmooth regularizers undermine the performance of traditional convex methods.<n>We propose a variance-free solution for ill-conditioned composite large-scale machine learning problems.
  arXiv  Detail & Related papers  (2025-01-27T10:36:45Z)
• Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models [33.911521719528686]
  Fine-tuning is powerful for adapting large language models to downstream tasks, but it often results in huge memory usages. A promising approach is using Zeroth-Order (ZO) gradients, which estimates to replace First-Order (FO) gradients. We introduce a novel layer-wise sparse computation and memory efficient ZO, named LeZO.
  arXiv  Detail & Related papers  (2024-10-13T12:47:37Z)
• Obtaining Lower Query Complexities through Lightweight Zeroth-Order Proximal Gradient Algorithms [65.42376001308064]
  We propose two variance reduced ZO estimators for complex gradient problems. We improve the state-of-the-art function complexities from $mathcalOleft(minfracdn1/2epsilon2, fracdepsilon3right)$ to $tildecalOleft(fracdepsilon2right)$.
  arXiv  Detail & Related papers  (2024-10-03T15:04:01Z)
• Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions [26.543628010637036]
  We introduce a novel adaptive reduction method that achieves an optimal convergence rate of $mathcalO(log T)$ for non- functions. We also extend the proposed technique to obtain the same optimal rate of $mathcalO(log T)$ for compositional optimization.
  arXiv  Detail & Related papers  (2024-06-04T04:39:51Z)
• Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient [40.22217106270146]
  Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. In composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random estimation. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances.
  arXiv  Detail & Related papers  (2024-05-28T02:27:53Z)
• A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport [92.96250725599958]
  Kernel-based optimal transport (OT) estimators offer an alternative, functional estimation procedure to address OT problems from samples. We show that our SSN method achieves a global convergence rate of $O (1/sqrtk)$, and a local quadratic convergence rate under standard regularity conditions.
  arXiv  Detail & Related papers  (2023-10-21T18:48:45Z)
• On Convergence of Incremental Gradient for Non-Convex Smooth Functions [63.51187646914962]
  In machine learning and network optimization, algorithms like shuffle SGD are popular due to minimizing the number of misses and good cache. This paper delves into the convergence properties SGD algorithms with arbitrary data ordering.
  arXiv  Detail & Related papers  (2023-05-30T17:47:27Z)
• Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization [61.26619639722804]
  We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
  arXiv  Detail & Related papers  (2022-02-26T19:10:48Z)
• Towards Noise-adaptive, Problem-adaptive Stochastic Gradient Descent [7.176107039687231]
  We design step-size schemes that make gradient descent (SGD) adaptive to (i) the noise. We prove that $T$ iterations of SGD with Nesterov iterations can be near optimal. Compared to other step-size schemes, we demonstrate the effectiveness of a novel novel exponential step-size scheme.
  arXiv  Detail & Related papers  (2021-10-21T19:22:14Z)
• Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning [52.76230802067506]
  A novel model-free algorithm is proposed to minimize regret in episodic reinforcement learning. The proposed algorithm employs an em early-settled reference update rule, with the aid of two Q-learning sequences. The design principle of our early-settled variance reduction method might be of independent interest to other RL settings.
  arXiv  Detail & Related papers  (2021-10-09T21:13:48Z)
• Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning [54.01682318834995]
  Preconditioning is a highly effective step for any iterative method involving matrix-vector multiplication. We prove that preconditioning has an additional benefit that has been previously unexplored. It simultaneously can reduce variance at essentially negligible cost.
  arXiv  Detail & Related papers  (2021-07-01T06:43:11Z)
• 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)
• Correcting Momentum with Second-order Information [50.992629498861724]
  We develop a new algorithm for non-critical optimization that finds an $O(epsilon)$epsilon point in the optimal product. We validate our results on a variety of large-scale deep learning benchmarks and architectures.
  arXiv  Detail & Related papers  (2021-03-04T19:01:20Z)
• A Variance Controlled Stochastic Method with Biased Estimation for Faster Non-convex Optimization [0.0]
  We propose a new technique, em variance controlled gradient (VCSG), to improve the performance of the reduced gradient (SVRG) $lambda$ is introduced in VCSG to avoid over-reducing a variance by SVRG. $mathcalO(min1/epsilon3/2,n1/4/epsilon)$ number of gradient evaluations, which improves the leading gradient complexity.
  arXiv  Detail & Related papers  (2021-02-19T12:22:56Z)
• 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)

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.