Eliminating Meta Optimization Through Self-Referential Meta Learning

• URL: http://arxiv.org/abs/2212.14392v1
• Date: Thu, 29 Dec 2022 17:53:40 GMT
• Title: Eliminating Meta Optimization Through Self-Referential Meta Learning
• Authors: Louis Kirsch, J\"urgen Schmidhuber
• Abstract summary: We investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. A neural network self-modifies to solve bandit and classic control tasks, improves its self-modifications, and learns how to learn.
• Score: 5.584060970507506
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Meta Learning automates the search for learning algorithms. At the same time, it creates a dependency on human engineering on the meta-level, where meta learning algorithms need to be designed. In this paper, we investigate self-referential meta learning systems that modify themselves without the need for explicit meta optimization. We discuss the relationship of such systems to in-context and memory-based meta learning and show that self-referential neural networks require functionality to be reused in the form of parameter sharing. Finally, we propose fitness monotonic execution (FME), a simple approach to avoid explicit meta optimization. A neural network self-modifies to solve bandit and classic control tasks, improves its self-modifications, and learns how to learn, purely by assigning more computational resources to better performing solutions.

Related papers

• Fast Adaptation with Kernel and Gradient based Meta Leaning [4.763682200721131]
  We propose two algorithms to improve both the inner and outer loops of Model A Meta Learning (MAML) Our first algorithm redefines the optimization problem in the function space to update the model using closed-form solutions. In the outer loop, the second algorithm adjusts the learning of the meta-learner by assigning weights to the losses from each task of the inner loop.
  arXiv  Detail & Related papers  (2024-11-01T07:05:03Z)
• General-Purpose In-Context Learning by Meta-Learning Transformers [45.63069059498147]
  We show that Transformers and other black-box models can be meta-trained to act as general-purpose in-context learners. We characterize transitions between algorithms that generalize, algorithms that memorize, and algorithms that fail to meta-train at all. We propose practical interventions such as biasing the training distribution that improve the meta-training and meta-generalization of general-purpose in-context learning algorithms.
  arXiv  Detail & Related papers  (2022-12-08T18:30:22Z)
• Accelerating Gradient-based Meta Learner [2.1349209400003932]
  We propose various acceleration techniques to speed up meta learning algorithms such as MAML (Model Agnostic Meta Learning) We introduce a novel method of training tasks in clusters, which not only accelerates the meta learning process but also improves model accuracy performance.
  arXiv  Detail & Related papers  (2021-10-27T14:27:36Z)
• Bootstrapped Meta-Learning [48.017607959109924]
  We propose an algorithm that tackles a challenging meta-optimisation problem by letting the meta-learner teach itself. The algorithm first bootstraps a target from the meta-learner, then optimises the meta-learner by minimising the distance to that target under a chosen (pseudo-)metric. We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark, improve upon MAML in few-shot learning, and demonstrate how our approach opens up new possibilities.
  arXiv  Detail & Related papers  (2021-09-09T18:29:05Z)
• Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks [62.63852372239708]
  Meta learning aims to learn the learning methodology for machine learning from observed tasks, so as to generalize to new query tasks. We interpret such learning methodology as learning an explicit hyper- parameter prediction function shared by all training tasks. Such setting guarantees that the meta-learned learning methodology is able to flexibly fit diverse query tasks.
  arXiv  Detail & Related papers  (2021-07-06T04:05:08Z)
• Meta-Learning with Neural Tangent Kernels [58.06951624702086]
  We propose the first meta-learning paradigm in the Reproducing Kernel Hilbert Space (RKHS) induced by the meta-model's Neural Tangent Kernel (NTK) Within this paradigm, we introduce two meta-learning algorithms, which no longer need a sub-optimal iterative inner-loop adaptation as in the MAML framework. We achieve this goal by 1) replacing the adaptation with a fast-adaptive regularizer in the RKHS; and 2) solving the adaptation analytically based on the NTK theory.
  arXiv  Detail & Related papers  (2021-02-07T20:53:23Z)
• Modeling and Optimization Trade-off in Meta-learning [23.381986209234164]
  We introduce and rigorously define the trade-off between accurate modeling and ease in meta-learning. Taking MAML as a representative metalearning algorithm, we theoretically characterize the trade-off for general non risk functions as well as linear regression. We also empirically solve a trade-off for metareinforcement learning benchmarks.
  arXiv  Detail & Related papers  (2020-10-24T15:32:08Z)
• Fast Few-Shot Classification by Few-Iteration Meta-Learning [173.32497326674775]
  We introduce a fast optimization-based meta-learning method for few-shot classification. Our strategy enables important aspects of the base learner objective to be learned during meta-training. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-10-01T15:59:31Z)
• Meta-Gradient Reinforcement Learning with an Objective Discovered Online [54.15180335046361]
  We propose an algorithm based on meta-gradient descent that discovers its own objective, flexibly parameterised by a deep neural network. Because the objective is discovered online, it can adapt to changes over time. On the Atari Learning Environment, the meta-gradient algorithm adapts over time to learn with greater efficiency.
  arXiv  Detail & Related papers  (2020-07-16T16:17:09Z)
• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? [72.00712736992618]
  We show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of self-distillation. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.
  arXiv  Detail & Related papers  (2020-03-25T17:58:42Z)

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.