Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering

• URL: http://arxiv.org/abs/2011.04803v1
• Date: Mon, 9 Nov 2020 22:07:30 GMT
• Title: Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering
• Authors: Ricky T. Q. Chen, Dami Choi, Lukas Balles, David Duvenaud, Philipp Hennig
• Abstract summary: 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.
• Score: 53.523517926927894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such as the curvature can help de-sensitize common hyperparameters. Based on this intuition, we explore the use of exact per-sample Hessian-vector products and gradients to construct optimizers that are self-tuning and hyperparameter-free. Based on a dynamics model of the gradient, we derive a process which leads to a curvature-corrected, noise-adaptive online gradient estimate. The smoothness of our updates makes it more amenable to simple step size selection schemes, which we also base off of our estimates quantities. We prove that our model-based procedure converges in the noisy quadratic setting. Though we do not see similar gains in deep learning tasks, we can match the performance of well-tuned optimizers and ultimately, this is an interesting step for constructing self-tuning optimizers.

Related papers

• Multi-fidelity Constrained Optimization for Stochastic Black Box Simulators [1.6385815610837167]
  We introduce the algorithm Scout-Nd (Stochastic Constrained Optimization for N dimensions) to tackle the issues mentioned earlier. Scout-Nd efficiently estimates the gradient, reduces the noise of the estimator gradient, and applies multi-fidelity schemes to further reduce computational effort. We validate our approach on standard benchmarks, demonstrating its effectiveness in optimizing parameters highlighting better performance compared to existing methods.
  arXiv  Detail & Related papers  (2023-11-25T23:36:38Z)
• Online Sensitivity Optimization in Differentially Private Learning [8.12606646175019]
  We present a novel approach to dynamically optimize the clipping threshold. We treat this threshold as an additional learnable parameter, establishing a clean relationship between the threshold and the cost function. Our method is thoroughly assessed against alternative fixed and adaptive strategies across diverse datasets, tasks, model dimensions, and privacy levels.
  arXiv  Detail & Related papers  (2023-10-02T00:30:49Z)
• Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels [78.6096486885658]
  We introduce lower bounds to the linearized Laplace approximation of the marginal likelihood. These bounds are amenable togradient-based optimization and allow to trade off estimation accuracy against computational complexity.
  arXiv  Detail & Related papers  (2023-06-06T19:02:57Z)
• Optimization using Parallel Gradient Evaluations on Multiple Parameters [51.64614793990665]
  We propose a first-order method for convex optimization, where gradients from multiple parameters can be used during each step of gradient descent. Our method uses gradients from multiple parameters in synergy to update these parameters together towards the optima.
  arXiv  Detail & Related papers  (2023-02-06T23:39:13Z)
• 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)
• Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes [4.355567556995855]
  We propose Avare, a simple and efficient algorithm for adaptive importance sampling for finite-sum optimization and sampling with decreasing step-sizes. Under standard technical conditions, we show that Avare achieves $mathcalO(T2/3)$ and $mathcalO(T5/6)$ dynamic regret for SGD and SGLD respectively when run with $mathcalO(T5/6)$ step sizes.
  arXiv  Detail & Related papers  (2021-03-23T00:28:15Z)
• Hyperboost: Hyperparameter Optimization by Gradient Boosting surrogate models [0.4079265319364249]
  Current state-of-the-art methods leverage Random Forests or Gaussian processes to build a surrogate model. We propose a new surrogate model based on gradient boosting. We demonstrate empirically that the new method is able to outperform some state-of-the art techniques across a reasonable sized set of classification problems.
  arXiv  Detail & Related papers  (2021-01-06T22:07:19Z)
• 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)
• A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning [95.85269649177336]
  ZO optimization iteratively performs three major steps: gradient estimation, descent direction, and solution update. We demonstrate promising applications of ZO optimization, such as evaluating and generating explanations from black-box deep learning models, and efficient online sensor management.
  arXiv  Detail & Related papers  (2020-06-11T06:50:35Z)
• 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.