Regularized Top-$k$: A Bayesian Framework for Gradient Sparsification

• URL: http://arxiv.org/abs/2501.05633v1
• Date: Fri, 10 Jan 2025 00:32:46 GMT
• Title: Regularized Top-$k$: A Bayesian Framework for Gradient Sparsification
• Authors: Ali Bereyhi, Ben Liang, Gary Boudreau, Ali Afana,
• Abstract summary: This work proposes a novel sparsification scheme that controls the learning rate scaling of error accumulation. Using the prior distribution inherited from Top-$k$, we derive a new sparsification algorithm which can be interpreted as a regularized form of Top-$k$.
• Score: 27.246907664193156
• License:
• Abstract: Error accumulation is effective for gradient sparsification in distributed settings: initially-unselected gradient entries are eventually selected as their accumulated error exceeds a certain level. The accumulation essentially behaves as a scaling of the learning rate for the selected entries. Although this property prevents the slow-down of lateral movements in distributed gradient descent, it can deteriorate convergence in some settings. This work proposes a novel sparsification scheme that controls the learning rate scaling of error accumulation. The development of this scheme follows two major steps: first, gradient sparsification is formulated as an inverse probability (inference) problem, and the Bayesian optimal sparsification mask is derived as a maximum-a-posteriori estimator. Using the prior distribution inherited from Top-$k$, we derive a new sparsification algorithm which can be interpreted as a regularized form of Top-$k$. We call this algorithm regularized Top-$k$ (RegTop-$k$). It utilizes past aggregated gradients to evaluate posterior statistics of the next aggregation. It then prioritizes the local accumulated gradient entries based on these posterior statistics. We validate our derivation through numerical experiments. In distributed linear regression, it is observed that while Top-$k$ remains at a fixed distance from the global optimum, RegTop-$k$ converges to the global optimum at significantly higher compression ratios. We further demonstrate the generalization of this observation by employing RegTop-$k$ in distributed training of ResNet-18 on CIFAR-10, where it noticeably outperforms Top-$k$.

Related papers

• Novel Gradient Sparsification Algorithm via Bayesian Inference [27.246907664193156]
  This paper proposes a novel sparsification algorithm called regularized Top-$k$ (RegTop-$k$) that controls the learning rate scaling of error accumulation. Numerical experiments with ResNet-18 on CIFAR-10 show that RegTop-$k$ achieves about $8%$ higher accuracy than standard Top-$k$.
  arXiv  Detail & Related papers  (2024-09-23T10:42:34Z)
• Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates [15.27596975662702]
  We explore algorithms achieving optimal rates of DP optimization with heavy-tailed gradients. Our results match the minimax lower bound in citekamath2022, indicating that the theoretical limit of convex optimization under DP is achievable.
  arXiv  Detail & Related papers  (2024-08-19T11:07:05Z)
• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• SIMPLE: A Gradient Estimator for $k$-Subset Sampling [42.38652558807518]
  In this work, we fall back to discrete $k$-subset sampling on the forward pass. We show that our gradient estimator, SIMPLE, exhibits lower bias and variance compared to state-of-the-art estimators. Empirical results show improved performance on learning to explain and sparse linear regression.
  arXiv  Detail & Related papers  (2022-10-04T22:33:16Z)
• High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails [55.561406656549686]
  We consider non- Hilbert optimization using first-order algorithms for which the gradient estimates may have tails. We show that a combination of gradient, momentum, and normalized gradient descent convergence to critical points in high-probability with best-known iteration for smooth losses.
  arXiv  Detail & Related papers  (2021-06-28T00:17:01Z)
• Stochastic Bias-Reduced Gradient Methods [44.35885731095432]
  We develop a new primitive for optimization: a low-bias, low-cost smoothing of ther $x_star$ of any bound of the Moreau-Yoshida function.
  arXiv  Detail & Related papers  (2021-06-17T13:33:05Z)
• Gradient Boosted Binary Histogram Ensemble for Large-scale Regression [60.16351608335641]
  We propose a gradient boosting algorithm for large-scale regression problems called textitGradient Boosted Binary Histogram Ensemble (GBBHE) based on binary histogram partition and ensemble learning. In the experiments, compared with other state-of-the-art algorithms such as gradient boosted regression tree (GBRT), our GBBHE algorithm shows promising performance with less running time on large-scale datasets.
  arXiv  Detail & Related papers  (2021-06-03T17:05:40Z)
• 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)
• Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds [72.63031036770425]
  We propose differentially private (DP) algorithms for bound non-dimensional optimization. We demonstrate two popular deep learning methods on the empirical advantages over standard gradient methods.
  arXiv  Detail & Related papers  (2020-06-24T06:01:24Z)
• Carath\'eodory Sampling for Stochastic Gradient Descent [79.55586575988292]
  We present an approach that is inspired by classical results of Tchakaloff and Carath'eodory about measure reduction. We adaptively select the descent steps where the measure reduction is carried out. We combine this with Block Coordinate Descent so that measure reduction can be done very cheaply.
  arXiv  Detail & Related papers  (2020-06-02T17:52:59Z)
• 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.