A New First-Order Meta-Learning Algorithm with Convergence Guarantees
- URL: http://arxiv.org/abs/2409.03682v1
- Date: Thu, 5 Sep 2024 16:37:26 GMT
- Title: A New First-Order Meta-Learning Algorithm with Convergence Guarantees
- Authors: El Mahdi Chayti, Martin Jaggi,
- Abstract summary: Gradient-based meta-learning, especially MAML, has emerged as a viable solution to accomplish this goal.
One problem MAML encounters is its computational and memory burdens needed to compute the meta-gradients.
We propose a new first-order variant of MAML that we prove converges to a stationary point of the MAML objective, unlike other first-order variants.
- Score: 37.85411810113886
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Learning new tasks by drawing on prior experience gathered from other (related) tasks is a core property of any intelligent system. Gradient-based meta-learning, especially MAML and its variants, has emerged as a viable solution to accomplish this goal. One problem MAML encounters is its computational and memory burdens needed to compute the meta-gradients. We propose a new first-order variant of MAML that we prove converges to a stationary point of the MAML objective, unlike other first-order variants. We also show that the MAML objective does not satisfy the smoothness assumption assumed in previous works; we show instead that its smoothness constant grows with the norm of the meta-gradient, which theoretically suggests the use of normalized or clipped-gradient methods compared to the plain gradient method used in previous works. We validate our theory on a synthetic experiment.
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) - Convergence of First-Order Algorithms for Meta-Learning with Moreau
Envelopes [6.935471115003109]
We show the convergence of First-Order Model-Agnostic Meta-Learning (FO-MAML) to the vicinity of a solution of objective Moreau.
Our main theoretical achievement is a theoretical improvement upon the inexact SGD framework.
arXiv Detail & Related papers (2023-01-17T11:04:10Z) - Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language
Transfer Learning [59.38343286807997]
We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks.
Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients.
We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
arXiv Detail & Related papers (2022-03-09T17:26:53Z) - Meta-Learning with Adjoint Methods [16.753336086160598]
A Meta-Learning (MAML) is widely used to find a good initialization for a family of tasks.
Despite its success, a critical challenge in MAML is to calculate the gradient w.r.t the initialization of a long training trajectory for the sampled tasks.
We propose Adjoint MAML (A-MAML) to address this problem.
We demonstrate the advantage of our approach in both synthetic and real-world meta-learning tasks.
arXiv Detail & Related papers (2021-10-16T01:18:50Z) - MAML is a Noisy Contrastive Learner [72.04430033118426]
Model-agnostic meta-learning (MAML) is one of the most popular and widely-adopted meta-learning algorithms nowadays.
We provide a new perspective to the working mechanism of MAML and discover that: MAML is analogous to a meta-learner using a supervised contrastive objective function.
We propose a simple but effective technique, zeroing trick, to alleviate such interference.
arXiv Detail & Related papers (2021-06-29T12:52:26Z) - Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and
Personalized Federated Learning [56.17603785248675]
Model-agnostic meta-learning (MAML) has become a popular research area.
Existing MAML algorithms rely on the episode' idea by sampling a few tasks and data points to update the meta-model at each iteration.
This paper proposes memory-based algorithms for MAML that converge with vanishing error.
arXiv Detail & Related papers (2021-06-09T08:47:58Z) - Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning [23.135033752967598]
We consider the novel problem of repurposing pretrained MAML checkpoints to solve new few-shot classification tasks.
Because of the potential distribution mismatch, the original MAML steps may no longer be optimal.
We propose an alternative metatesting procedure and combine adversarial training and uncertainty-based stepsize adaptation.
arXiv Detail & Related papers (2021-03-16T12:53:09Z) - 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) - Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning [63.64636047748605]
We develop a new theoretical framework to provide convergence guarantee for the general multi-step MAML algorithm.
In particular, our results suggest that an inner-stage step needs to be chosen inversely proportional to $N$ of inner-stage steps in order for $N$ MAML to have guaranteed convergence.
arXiv Detail & Related papers (2020-02-18T19:17:54Z)
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.