Forward Gradient-Based Frank-Wolfe Optimization for Memory Efficient Deep Neural Network Training
- URL: http://arxiv.org/abs/2403.12511v1
- Date: Tue, 19 Mar 2024 07:25:36 GMT
- Title: Forward Gradient-Based Frank-Wolfe Optimization for Memory Efficient Deep Neural Network Training
- Authors: M. Rostami, S. S. Kia,
- Abstract summary: This paper focuses on analyzing the performance of the well-known Frank-Wolfe algorithm.
We show the proposed algorithm does converge to the optimal solution with a sub-linear rate of convergence.
In contrast, the standard Frank-Wolfe algorithm, when provided with access to the Projected Forward Gradient, fails to converge to the optimal solution.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Training a deep neural network using gradient-based methods necessitates the calculation of gradients at each level. However, using backpropagation or reverse mode differentiation, to calculate the gradients necessities significant memory consumption, rendering backpropagation an inefficient method for computing gradients. This paper focuses on analyzing the performance of the well-known Frank-Wolfe algorithm, a.k.a. conditional gradient algorithm by having access to the forward mode of automatic differentiation to compute gradients. We provide in-depth technical details that show the proposed Algorithm does converge to the optimal solution with a sub-linear rate of convergence by having access to the noisy estimate of the true gradient obtained in the forward mode of automated differentiation, referred to as the Projected Forward Gradient. In contrast, the standard Frank-Wolfe algorithm, when provided with access to the Projected Forward Gradient, fails to converge to the optimal solution. We demonstrate the convergence attributes of our proposed algorithms using a numerical example.
Related papers
- An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization [15.652261277429968]
We propose an enhanced zeroth-order convex computation Frank-Wolfe to address constrained finite-sum optimization problems.
Our method introduces a novel double variance reduction framework that effectively reduces the approximation induced by zeroth-order oracles.
arXiv Detail & Related papers (2025-01-13T10:53:19Z) - Sample-efficient Bayesian Optimisation Using Known Invariances [56.34916328814857]
We show that vanilla and constrained BO algorithms are inefficient when optimising invariant objectives.
We derive a bound on the maximum information gain of these invariant kernels.
We use our method to design a current drive system for a nuclear fusion reactor, finding a high-performance solution.
arXiv Detail & Related papers (2024-10-22T12:51:46Z) - Randomized Forward Mode of Automatic Differentiation For Optimization
Algorithms [0.0]
We present a randomized forward mode gradient (RFG) as an alternative to backpropagation.
The probability distribution of the random vector determines the statistical properties of RFG.
By replacing gradient with RFG, a class of RFG-based optimization algorithms is obtained.
arXiv Detail & Related papers (2023-10-22T04:02:39Z) - Random-reshuffled SARAH does not need a full gradient computations [61.85897464405715]
The StochAstic Recursive grAdientritHm (SARAH) algorithm is a variance reduced variant of the Gradient Descent (SGD) algorithm.
In this paper, we remove the necessity of a full gradient.
The aggregated gradients serve as an estimate of a full gradient in the SARAH algorithm.
arXiv Detail & Related papers (2021-11-26T06:00:44Z) - Differentiable Annealed Importance Sampling and the Perils of Gradient
Noise [68.44523807580438]
Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation.
Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective.
We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
arXiv Detail & Related papers (2021-07-21T17:10:14Z) - 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) - Projection-Free Adaptive Gradients for Large-Scale Optimization [22.0439695290991]
Frank-Wolfe algorithms occupy a unique position as they alleviate both computational burdens by querying only approximate first-order information from the objective.
We show that our method can improve the performance of adaptive algorithms for constrained optimization.
arXiv Detail & Related papers (2020-09-29T15:56:12Z) - Variance Reduction for Deep Q-Learning using Stochastic Recursive
Gradient [51.880464915253924]
Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance.
This paper introduces the framework for updating the gradient estimates in deep Q-learning, achieving a novel algorithm called SRG-DQN.
arXiv Detail & Related papers (2020-07-25T00:54:20Z) - An adaptive stochastic gradient-free approach for high-dimensional
blackbox optimization [0.0]
We propose an adaptive gradient-free (ASGF) approach for high-dimensional non-smoothing problems.
We illustrate the performance of this method on benchmark global problems and learning tasks.
arXiv Detail & Related papers (2020-06-18T22:47:58Z) - Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization [71.03797261151605]
Adaptivity is an important yet under-studied property in modern optimization theory.
Our algorithm is proved to achieve the best-available convergence for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives.
arXiv Detail & Related papers (2020-02-13T05:42:27Z)
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.