Transformer-Based Learned Optimization

• URL: http://arxiv.org/abs/2212.01055v4
• Date: Wed, 28 Jun 2023 09:23:08 GMT
• Title: Transformer-Based Learned Optimization
• Authors: Erik G\"artner, Luke Metz, Mykhaylo Andriluka, C. Daniel Freeman, Cristian Sminchisescu
• Abstract summary: We propose a new approach to learned optimization where we represent the computation's update step using a neural network. Our innovation is a new neural network architecture inspired by the classic BFGS algorithm. We demonstrate the advantages of our approach on a benchmark composed of objective functions traditionally used for the evaluation of optimization algorithms.
• Score: 37.84626515073609
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a new approach to learned optimization where we represent the computation of an optimizer's update step using a neural network. The parameters of the optimizer are then learned by training on a set of optimization tasks with the objective to perform minimization efficiently. Our innovation is a new neural network architecture, Optimus, for the learned optimizer inspired by the classic BFGS algorithm. As in BFGS, we estimate a preconditioning matrix as a sum of rank-one updates but use a Transformer-based neural network to predict these updates jointly with the step length and direction. In contrast to several recent learned optimization-based approaches, our formulation allows for conditioning across the dimensions of the parameter space of the target problem while remaining applicable to optimization tasks of variable dimensionality without retraining. We demonstrate the advantages of our approach on a benchmark composed of objective functions traditionally used for the evaluation of optimization algorithms, as well as on the real world-task of physics-based visual reconstruction of articulated 3d human motion.

Related papers

• Operator SVD with Neural Networks via Nested Low-Rank Approximation [19.562492156734653]
  This paper proposes a new optimization framework based on the low-rank approximation characterization of a truncated singular value decomposition. New techniques called emphnesting for learning the top-$L$ singular values and singular functions in the correct order. We demonstrate the effectiveness of the proposed framework for use cases in computational physics and machine learning.
  arXiv  Detail & Related papers  (2024-02-06T03:06:06Z)
• Neural lasso: a unifying approach of lasso and neural networks [0.27624021966289597]
  The statistical technique lasso for variable selection is represented through a neural network. It is observed that, although both the statistical approach and its neural version have the same objective function, they differ due to their optimization. A new optimization algorithm for identifying the significant variables emerged.
  arXiv  Detail & Related papers  (2023-09-07T15:17:10Z)
• VeLO: Training Versatile Learned Optimizers by Scaling Up [67.90237498659397]
  We leverage the same scaling approach behind the success of deep learning to learn versatiles. We train an ingest for deep learning which is itself a small neural network that ingests and outputs parameter updates. We open source our learned, meta-training code, the associated train test data, and an extensive benchmark suite with baselines at velo-code.io.
  arXiv  Detail & Related papers  (2022-11-17T18:39:07Z)
• Towards Theoretically Inspired Neural Initialization Optimization [66.04735385415427]
  We propose a differentiable quantity, named GradCosine, with theoretical insights to evaluate the initial state of a neural network. We show that both the training and test performance of a network can be improved by maximizing GradCosine under norm constraint. Generalized from the sample-wise analysis into the real batch setting, NIO is able to automatically look for a better initialization with negligible cost.
  arXiv  Detail & Related papers  (2022-10-12T06:49:16Z)
• Learning to Optimize Quasi-Newton Methods [22.504971951262004]
  This paper introduces a novel machine learning called LODO, which tries to online meta-learn the best preconditioner during optimization. Unlike other L2O methods, LODO does not require any meta-training on a training task distribution. We show that our gradient approximates the inverse Hessian in noisy loss landscapes and is capable of representing a wide range of inverse Hessians.
  arXiv  Detail & Related papers  (2022-10-11T03:47:14Z)
• Teaching Networks to Solve Optimization Problems [13.803078209630444]
  We propose to replace the iterative solvers altogether with a trainable parametric set function. We show the feasibility of learning such parametric (set) functions to solve various classic optimization problems.
  arXiv  Detail & Related papers  (2022-02-08T19:13:13Z)
• Reverse engineering learned optimizers reveals known and novel mechanisms [50.50540910474342]
  Learneds are algorithms that can themselves be trained to solve optimization problems. Our results help elucidate the previously murky understanding of how learneds work, and establish tools for interpreting future learneds.
  arXiv  Detail & Related papers  (2020-11-04T07:12:43Z)
• Adaptive pruning-based optimization of parameterized quantum circuits [62.997667081978825]
  Variisy hybrid quantum-classical algorithms are powerful tools to maximize the use of Noisy Intermediate Scale Quantum devices. We propose a strategy for such ansatze used in variational quantum algorithms, which we call "Efficient Circuit Training" (PECT) Instead of optimizing all of the ansatz parameters at once, PECT launches a sequence of variational algorithms.
  arXiv  Detail & Related papers  (2020-10-01T18:14:11Z)
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves [53.37905268850274]
  We introduce a new, hierarchical, neural network parameterized, hierarchical with access to additional features such as validation loss to enable automatic regularization. Most learneds have been trained on only a single task, or a small number of tasks. We train ours on thousands of tasks, making use of orders of magnitude more compute, resulting in generalizes that perform better to unseen tasks.
  arXiv  Detail & Related papers  (2020-09-23T16:35:09Z)
• NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control [22.120942106939122]
  We propose the use of adaptive search as a building block for general, non- neural optimization operations. We benchmark it against two existing alternatives on a synthetic energy-based structured task, and showcase its use in optimal control applications.
  arXiv  Detail & Related papers  (2020-06-22T03:40:36Z)
• 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)

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.