Stochastic Gradient Optimization with Model-Assisted Sampling

• URL: http://arxiv.org/abs/2606.27171v1
• Date: Thu, 25 Jun 2026 15:39:19 GMT
• Title: Stochastic Gradient Optimization with Model-Assisted Sampling
• Abstract summary: We propose a model-assisted sampling framework that interprets mini-batch gradients through survey sampling theory.<n>Our aim is to bridge machine learning optimization and survey sampling theory by combining their perspectives on sample-based estimation and variance reduction.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work addresses the problem of variance in stochastic gradient estimation for machine learning optimization. Deep learning relies on mini-batch methods such as stochastic gradient descent, which approximate full gradients but introduce noise, creating trade-offs between convergence stability, speed, and generalization. Existing methods, including variance reduction techniques (e.g., SVRG and SAG) and adaptive optimizers, aim to mitigate gradient noise but may introduce additional computational overhead. We propose a model-assisted sampling framework that interprets mini-batch gradients through survey sampling theory, treating the dataset as a fixed finite population and gradients as sample-based estimates. Our aim is to bridge machine learning optimization and survey sampling theory by combining their perspectives on sample-based estimation and variance reduction. By incorporating auxiliary gradient-prediction models, we construct more efficient gradient estimators, with uniform sampling arising as a special case when no auxiliary information is used. Our approach integrates easily with existing optimizers, improving efficiency without altering their dynamics. Empirical results on synthetic and six benchmark datasets show performance gains in 71-86% of the experiments, particularly for medium-sized input spaces in our benchmarks. Notably, with momentum-based optimizers such as AdamW, the proposed estimator achieves clearly better generalization in roughly half the training epochs compared to baseline estimator.

Related papers

• Instance-optimal stochastic convex optimization: Can we improve upon sample-average and robust stochastic approximation? [19.235225166737354]
  We study the unconstrained minimization of a smooth and strongly convex population loss function under an oracle that introduces both additive and multiplicative noise.<n>Results show that an accelerated variant of VISOR is instance-optimal, achieving the best possible sample complexity up to logarithmic factors.
  arXiv  Detail & Related papers  (2026-03-26T17:12:01Z)
• On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization [57.179679246370114]
  A potential limitation of existing methods is the bias inherent in most perturbation estimators unless a stepsize is proposed.<n>We propose a novel family of unbiased gradient scaling estimators that eliminate bias while maintaining favorable construction.
  arXiv  Detail & Related papers  (2025-10-22T18:25:43Z)
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models [90.45197506653341]
  Large reasoning models generate intermediate reasoning traces before producing final answers.<n> aligning LRMs with human preferences, a crucial prerequisite for model deployment, remains underexplored.<n>A common workaround optimized a single sampled trajectory, which introduces substantial gradient variance from trace sampling.
  arXiv  Detail & Related papers  (2025-10-06T17:58:01Z)
• Zero-Variance Gradients for Variational Autoencoders [32.818968022327866]
  Training deep generative models like Variational Autoencoders (VAEs) is often hindered by the need to backpropagate gradients through sampling of their latent variables.<n>In this paper, we propose a new perspective that sidesteps this problem, which we call Silent Gradients.<n>Instead of improving estimators, we leverage specific decoder architectures analytically to compute the expected ELBO, yielding a gradient with zero variance.
  arXiv  Detail & Related papers  (2025-08-05T15:54:21Z)
• FLOPS: Forward Learning with OPtimal Sampling [1.694989793927645]
  gradient-based computation methods have recently gained focus for learning with only forward passes, also referred to as queries.<n> Conventional forward learning consumes enormous queries on each data point for accurate gradient estimation through Monte Carlo sampling.<n>We propose to allocate the optimal number of queries over each data in one batch during training to achieve a good balance between estimation accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2024-10-08T12:16:12Z)
• Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms [13.134564730161983]
  This paper adopts a novel approach to deep learning optimization, focusing on gradient descent (SGD) and its variants. We show that SGD and its variants demonstrate performance on par with flat-minimas like SAM, albeit with half the gradient evaluations. Our study uncovers several key findings regarding the relationship between training loss and hold-out accuracy, as well as the comparable performance of SGD and noise-enabled variants.
  arXiv  Detail & Related papers  (2024-03-01T14:55:22Z)
• Data Pruning via Moving-one-Sample-out [61.45441981346064]
  We propose a novel data-pruning approach called moving-one-sample-out (MoSo) MoSo aims to identify and remove the least informative samples from the training set. Experimental results demonstrate that MoSo effectively mitigates severe performance degradation at high pruning ratios.
  arXiv  Detail & Related papers  (2023-10-23T08:00:03Z)
• Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptotics [18.93569692490218]
  tuning of gradient algorithms often based on trial-and-error rather than generalizable theory. We show that averaging with a large fixed step size is robust to the choice of tuning parameters. We lay the foundation for a systematic analysis of other gradient Monte Carlo algorithms.
  arXiv  Detail & Related papers  (2022-07-25T17:58:09Z)
• Adaptive Optimization with Examplewise Gradients [23.504973357538418]
  We propose a new, more general approach to the design of gradient-based optimization methods for machine learning. In this new framework, iterations assume access to a batch of estimates per parameter, rather than a single estimate. This better reflects the information that is actually available in typical machine learning setups.
  arXiv  Detail & Related papers  (2021-11-30T23:37:01Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering [53.523517926927894]
  We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics. We prove that our model-based procedure converges in noisy gradient setting. This is an interesting step for constructing self-tuning quadratics.
  arXiv  Detail & Related papers  (2020-11-09T22:07:30Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.