Feasibility and Transferability of Transfer Learning: A Mathematical Framework

• URL: http://arxiv.org/abs/2301.11542v1
• Date: Fri, 27 Jan 2023 05:54:53 GMT
• Title: Feasibility and Transferability of Transfer Learning: A Mathematical Framework
• Authors: Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum
• Abstract summary: We build for the first time a mathematical framework for the general procedure of transfer learning. We also propose a novel concept of transfer risk to evaluate transferability of transfer learning.
• Score: 4.031388559887924
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. Despite its numerous empirical successes, theoretical analysis for transfer learning is limited. In this paper we build for the first time, to the best of our knowledge, a mathematical framework for the general procedure of transfer learning. Our unique reformulation of transfer learning as an optimization problem allows for the first time, analysis of its feasibility. Additionally, we propose a novel concept of transfer risk to evaluate transferability of transfer learning. Our numerical studies using the Office-31 dataset demonstrate the potential and benefits of incorporating transfer risk in the evaluation of transfer learning performance.

Related papers

• Bayesian Transfer Learning [13.983016833412307]
  "Transfer learning" seeks to improve inference and/or predictive accuracy on a domain of interest by leveraging data from related domains. This article highlights Bayesian approaches to transfer learning, which have received relatively limited attention despite their innate compatibility with the notion of drawing upon prior knowledge to guide new learning tasks. We discuss how these methods address the problem of finding the optimal information to transfer between domains, which is a central question in transfer learning.
  arXiv  Detail & Related papers  (2023-12-20T23:38:17Z)
• Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges [21.559563253625207]
  Transfer learning is a conceptually-enticing paradigm in pursuit of truly intelligent embodied agents. We provide the first taxonomy of its kind considering the key concepts of robot, task, and environment.
  arXiv  Detail & Related papers  (2023-11-29T19:40:10Z)
• Risk of Transfer Learning and its Applications in Finance [2.966069495345018]
  We propose a novel concept of transfer risk and analyze its properties to evaluate transferability of transfer learning. Numerical results demonstrate a strong correlation between transfer risk and overall transfer learning performance.
  arXiv  Detail & Related papers  (2023-11-06T17:23:54Z)
• Transfer Learning for Portfolio Optimization [4.031388559887924]
  We introduce a novel concept called "transfer risk", within the optimization framework of transfer learning. A series of numerical experiments are conducted from three categories: cross-continent transfer, cross-sector transfer, and cross-frequency transfer.
  arXiv  Detail & Related papers  (2023-07-25T14:48:54Z)
• Feasibility of Transfer Learning: A Mathematical Framework [4.530876736231948]
  It begins by establishing the necessary mathematical concepts and constructing a mathematical framework for transfer learning. It then identifies and formulates the three-step transfer learning procedure as an optimization problem, allowing for the resolution of the feasibility issue.
  arXiv  Detail & Related papers  (2023-05-22T12:44:38Z)
• Rethinking Importance Weighting for Transfer Learning [71.81262398144946]
  Key assumption in supervised learning is that training and test data follow the same probability distribution. As real-world machine learning tasks are becoming increasingly complex, novel approaches are explored to cope with such challenges.
  arXiv  Detail & Related papers  (2021-12-19T14:35:25Z)
• Meta-learning Transferable Representations with a Single Target Domain [46.83481356352768]
  Fine-tuning and joint training do not always improve accuracy on downstream tasks. We propose Meta Representation Learning (MeRLin) to learn transferable features. MeRLin empirically outperforms previous state-of-the-art transfer learning algorithms on various real-world vision and NLP transfer learning benchmarks.
  arXiv  Detail & Related papers  (2020-11-03T01:57:37Z)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)
• Transfer Learning in Deep Reinforcement Learning: A Survey [64.36174156782333]
  Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. transfer learning has arisen to tackle various challenges faced by reinforcement learning.
  arXiv  Detail & Related papers  (2020-09-16T18:38:54Z)
• What is being transferred in transfer learning? [51.6991244438545]
  We show that when training from pre-trained weights, the model stays in the same basin in the loss landscape. We present that when training from pre-trained weights, the model stays in the same basin in the loss landscape and different instances of such model are similar in feature space and close in parameter space.
  arXiv  Detail & Related papers  (2020-08-26T17:23:40Z)
• Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach [55.83558520598304]
  We propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. We also describe how to design an efficient communication protocol to exploit heterogeneous knowledge. Our proposed framework, namely Learning and Teaching Categorical Reinforcement, shows promising performance on stabilizing and accelerating learning progress.
  arXiv  Detail & Related papers  (2020-02-06T11:31:04Z)

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.