Nonlinear Meta-Learning Can Guarantee Faster Rates

• URL: http://arxiv.org/abs/2307.10870v5
• Date: Tue, 20 May 2025 09:10:41 GMT
• Title: Nonlinear Meta-Learning Can Guarantee Faster Rates
• Abstract summary: We derive theoretical guarantees for meta-learning with nonlinear representations.<n>In particular, we show that additional biases can be mitigated with careful regularization.
• Score: 31.236026714761913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. The main aim of theoretical guarantees on the subject is to establish the extent to which convergence rates -- in learning a common representation -- \emph{may scale with the number $N$ of tasks} (as well as the number of samples per task). First steps in this setting demonstrate this property when both the shared representation amongst tasks, and task-specific regression functions, are linear. This linear setting readily reveals the benefits of aggregating tasks, e.g., via averaging arguments. In practice, however, the representation is often highly nonlinear, introducing nontrivial biases in each task that cannot easily be averaged out as in the linear case. In the present work, we derive theoretical guarantees for meta-learning with nonlinear representations. In particular, assuming the shared nonlinearity maps to an infinite dimensional reproducing kernel Hilbert space, we show that additional biases can be mitigated with careful regularization that leverages the smoothness of task-specific regression functions, yielding improved rates that scale with the number of tasks as desired.

Related papers

• Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety [2.538209532048867]
  We study the multi-task linear regression problem in the presence of contaminated tasks.<n>We introduce a relative balancedness condition, quantified by a balancedness constant, that compares each task's second moment with the average inlier geometry.<n>Our method achieves simultaneous adaptivity to task similarity, robustness to outliers, and safety outside favorable transfer regimes.
  arXiv  Detail & Related papers  (2026-05-16T19:06:54Z)
• Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning [0.0]
  We study offline multitask reinforcement learning in settings where multiple tasks share a low-rank representation of their action-value functions.<n>We analyze a multitask variant of fitted Q-iteration that jointly learns a shared representation and task-specific value functions.<n>Our results clarify the role of shared representations in multitask offline Q-learning and provide theoretical insight into when and how multitask structure can improve generalization.
  arXiv  Detail & Related papers  (2025-12-23T10:20:11Z)
• When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers [64.1656365676171]
  Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors. This paper theoretically prove the effectiveness of task addition in simultaneously learning a set of irrelevant or irrelevant tasks. We prove the proper selection for task arithmetic to achieve negation to out-of-domain tasks.
  arXiv  Detail & Related papers  (2025-04-15T08:04:39Z)
• Efficient Model Editing with Task-Localized Sparse Fine-tuning [14.792099973449794]
  We propose TaLoS which allows to build sparse task vectors with minimal interference without requiring explicit linearization.<n>We find that pre-trained models contain a subset of parameters with consistently low gradient sensitivity across tasks.<n>Our experiments prove that TaLoS improves training and inference efficiency while outperforming current methods in task addition and negation.
  arXiv  Detail & Related papers  (2025-04-03T14:20:06Z)
• Towards Understanding the Benefit of Multitask Representation Learning in Decision Process [47.57497888077687]
  Multitask Representation Learning (MRL) has emerged as a prevalent technique to improve sample efficiency in Reinforcement Learning (RL) Our work tries to fill the gap by extending the analysis to textitunknown non-linear representations, giving a comprehensive analysis for its mechanism in online and transfer learning setting. We formally prove that this approach yields a regret upper bound that outperforms the lower bound associated with learning $M$ separate tasks, marking the first demonstration of MRL's efficacy in a general function class.
  arXiv  Detail & Related papers  (2025-03-01T04:29:22Z)
• Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks [69.38572074372392]
  We present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks. Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks.
  arXiv  Detail & Related papers  (2023-07-13T16:39:08Z)
• Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning [23.45043290237396]
  MoSS is a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior in terms of performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization.
  arXiv  Detail & Related papers  (2023-04-29T15:46:19Z)
• Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness [15.14830455376279]
  We study how to learn from tasks with textitsimilar but not exactly the same linear representations, while dealing with outlier tasks.<n>We provide information-theoretic lower bounds to demonstrate that both methods are nearly textitminimax optimal in a large regime.<n>We also introduce a thresholding algorithm to adapt to an unknown intrinsic dimension.
  arXiv  Detail & Related papers  (2023-03-31T01:56:13Z)
• Self-Supervised Learning via Maximum Entropy Coding [57.56570417545023]
  We propose Maximum Entropy Coding (MEC) as a principled objective that explicitly optimize on the structure of the representation. MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking.
  arXiv  Detail & Related papers  (2022-10-20T17:58:30Z)
• Provable General Function Class Representation Learning in Multitask Bandits and MDPs [58.624124220900306]
  multitask representation learning is a popular approach in reinforcement learning to boost the sample efficiency. In this work, we extend the analysis to general function class representations. We theoretically validate the benefit of multitask representation learning within general function class for bandits and linear MDP.
  arXiv  Detail & Related papers  (2022-05-31T11:36:42Z)
• Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss [72.62029620566925]
  Recent works in self-supervised learning have advanced the state-of-the-art by relying on the contrastive learning paradigm. Our work analyzes contrastive learning without assuming conditional independence of positive pairs. We propose a loss that performs spectral decomposition on the population augmentation graph and can be succinctly written as a contrastive learning objective.
  arXiv  Detail & Related papers  (2021-06-08T07:41:02Z)
• How Fine-Tuning Allows for Effective Meta-Learning [50.17896588738377]
  We present a theoretical framework for analyzing representations derived from a MAML-like algorithm. We provide risk bounds on the best predictor found by fine-tuning via gradient descent, demonstrating that the algorithm can provably leverage the shared structure. This separation result underscores the benefit of fine-tuning-based methods, such as MAML, over methods with "frozen representation" objectives in few-shot learning.
  arXiv  Detail & Related papers  (2021-05-05T17:56:00Z)
• Conditional Meta-Learning of Linear Representations [57.90025697492041]
  Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. In this work we overcome this issue by inferring a conditioning function, mapping the tasks' side information into a representation tailored to the task at hand. We propose a meta-algorithm capable of leveraging this advantage in practice.
  arXiv  Detail & Related papers  (2021-03-30T12:02:14Z)
• Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning [28.2312127482203]
  This work explores a more general class of nonlinear tasks with applications ranging from binary classification to neural nets. We prove that subspace-based representations can be learned in a sample-efficient manner and provably benefit future tasks in terms of sample complexity.
  arXiv  Detail & Related papers  (2021-02-14T17:40:04Z)
• Learning an Interpretable Graph Structure in Multi-Task Learning [18.293397644865454]
  We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Our graph is learned simultaneously with model parameters of each task, thus it reflects the critical relationship among tasks in the specific prediction problem.
  arXiv  Detail & Related papers  (2020-09-11T18:58:14Z)
• The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning [50.21341246243422]
  Biased regularization and fine-tuning are two recent meta-learning approaches. We propose conditional meta-learning, inferring a conditioning function mapping task's side information into a meta- parameter vector. We then propose a convex meta-algorithm providing a comparable advantage also in practice.
  arXiv  Detail & Related papers  (2020-08-25T07:32:16Z)

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.