Meta-Learning Loss Functions for Deep Neural Networks
- URL: http://arxiv.org/abs/2406.09713v2
- Date: Sat, 29 Jun 2024 23:51:03 GMT
- Title: Meta-Learning Loss Functions for Deep Neural Networks
- Authors: Christian Raymond,
- Abstract summary: This thesis explores the concept of meta-learning to improve performance, through the often-overlooked component of the loss function.
The loss function is a vital component of a learning system, as it represents the primary learning objective, where success is determined and quantified by the system's ability to optimize for that objective successfully.
- Score: 2.4258031099152735
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even the most basic tasks. Meta-learning aims to resolve this issue by leveraging past experiences from similar learning tasks to embed the appropriate inductive biases into the learning system. Historically methods for meta-learning components such as optimizers, parameter initializations, and more have led to significant performance increases. This thesis aims to explore the concept of meta-learning to improve performance, through the often-overlooked component of the loss function. The loss function is a vital component of a learning system, as it represents the primary learning objective, where success is determined and quantified by the system's ability to optimize for that objective successfully.
Related papers
- Fast and Efficient Local Search for Genetic Programming Based Loss
Function Learning [12.581217671500887]
We propose a new meta-learning framework for task and model-agnostic loss function learning via a hybrid search approach.
Results show that the learned loss functions bring improved convergence, sample efficiency, and inference performance on tabulated, computer vision, and natural language processing problems.
arXiv Detail & Related papers (2024-03-01T02:20:04Z) - Online Loss Function Learning [13.744076477599707]
Loss function learning aims to automate the task of designing a loss function for a machine learning model.
We propose a new loss function learning technique for adaptively updating the loss function online after each update to the base model parameters.
arXiv Detail & Related papers (2023-01-30T19:22:46Z) - Concept Discovery for Fast Adapatation [42.81705659613234]
We introduce concept discovery to the few-shot learning problem, where we achieve more effective adaptation by meta-learning the structure among the data features.
Our proposed method Concept-Based Model-Agnostic Meta-Learning (COMAML) has been shown to achieve consistent improvements in the structured data for both synthesized datasets and real-world datasets.
arXiv Detail & Related papers (2023-01-19T02:33:58Z) - Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning [12.581217671500887]
We propose a new meta-learning framework for learning model-agnostic loss functions via a hybrid neuro-symbolic search approach.
Results show that the meta-learned loss functions discovered by the newly proposed method outperform both the cross-entropy loss and state-of-the-art loss function learning methods.
arXiv Detail & Related papers (2022-09-19T10:29:01Z) - Skill-based Meta-Reinforcement Learning [65.31995608339962]
We devise a method that enables meta-learning on long-horizon, sparse-reward tasks.
Our core idea is to leverage prior experience extracted from offline datasets during meta-learning.
arXiv Detail & Related papers (2022-04-25T17:58:19Z) - What Matters For Meta-Learning Vision Regression Tasks? [19.373532562905208]
This paper makes two main contributions that help understand this barely explored area.
First, we design two new types of cross-category level vision regression tasks, namely object discovery and pose estimation.
Second, we propose the addition of functional contrastive learning (FCL) over the task representations in Conditional Neural Processes (CNPs) and train in an end-to-end fashion.
arXiv Detail & Related papers (2022-03-09T17:28:16Z) - 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) - Importance Weighted Policy Learning and Adaptation [89.46467771037054]
We study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning.
The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior.
Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.
arXiv Detail & Related papers (2020-09-10T14:16:58Z) - Concept Learners for Few-Shot Learning [76.08585517480807]
We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions.
We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
arXiv Detail & Related papers (2020-07-14T22:04:17Z) - Provable Meta-Learning of Linear Representations [114.656572506859]
We provide fast, sample-efficient algorithms to address the dual challenges of learning a common set of features from multiple, related tasks, and transferring this knowledge to new, unseen tasks.
We also provide information-theoretic lower bounds on the sample complexity of learning these linear features.
arXiv Detail & Related papers (2020-02-26T18:21:34Z) - Automated Relational Meta-learning [95.02216511235191]
We propose an automated relational meta-learning framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph.
We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines.
arXiv Detail & Related papers (2020-01-03T07:02:25Z)
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.