paper-with-me

Papers

Phase Transitions in Transfer Learning for High-Dimensional Perceptrons

2021-01-06 · Oussama Dhifallah, Yue M. Lu

Transfer learning seeks to improve the generalization performance of a target task by exploiting the knowledge learned from a related source task. Central questions include deciding what information one should transfer and when transfer can be beneficial. The latter question is related to the so-called negative transfer phenomenon, where the transferred source information actually reduces the generalization performance of the target task. This happens when the two tasks are sufficiently dissimilar. In this paper, we present a theoretical analysis of transfer learning by studying a pair of related perceptron learning tasks. Despite the simplicity of our model, it reproduces several key phenomena observed in practice. Specifically, our asymptotic analysis reveals a phase transition from negative transfer to positive transfer as the similarity of the two tasks moves past a well-defined threshold.

📄 PDF Abstract BibTeX arXiv:2101.01918

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer LearningVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Unveiling phase transitions with machine learning

2019-04-02 · Askery Canabarro, Felipe Fernandes Fanchini, André Luiz Malvezzi, Rodrigo Pereira 외

The classification of phase transitions is a central and challenging task in condensed matter physics. Typically, it relies on the identification of order parameters and the analysis of singularities in the free energy a…

BIG-bench Machine LearningTransfer Learning

Rethinking Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics

2018-10-08 · Weizhi Zhu, Yifei HUANG, Yuan YAO

Margin enlargement over training data has been an important strategy since perceptrons in machine learning for the purpose of boosting the robustness of classifiers toward a good generalization ability. Yet Breiman (1999…

Generalization Bounds

Transfer learning of phase transitions in percolation and directed percolation

2021-12-31 · Jianmin Shen, Feiyi Liu, Shiyang Chen, Dian Xu 외

The latest advances of statistical physics have shown remarkable performance of machine learning in identifying phase transitions. In this paper, we apply domain adversarial neural network (DANN) based on transfer learni…

Transfer Learning

Neural models for prediction of spatially patterned phase transitions: methods and challenges

2025-05-14 · Daniel Dylewsky, Sonia Kéfi, Madhur Anand, Chris T. Bauch

Dryland vegetation ecosystems are known to be susceptible to critical transitions between alternative stable states when subjected to external forcing. Such transitions are often discussed through the framework of bifurc…

Detecting phase transitions in collective behavior using manifold's curvature

2015-09-23 · Kelum Gajamannage, Erik M. Bollt

If a given behavior of a multi-agent system restricts the phase variable to a invariant manifold, then we define a phase transition as change of physical characteristics such as speed, coordination, and structure. We def…