paper-with-me

홈 › Papers

Principled Curriculum Learning using Parameter Continuation Methods

2025-07-29 · Harsh Nilesh Pathak, Randy Paffenroth arxiv

In this work, we propose a parameter continuation method for the optimization of neural networks. There is a close connection between parameter continuation, homotopies, and curriculum learning. The methods we propose here are theoretically justified and practically effective for several problems in deep neural networks. In particular, we demonstrate better generalization performance than state-of-the-art optimization techniques such as ADAM for supervised and unsupervised learning tasks.

📄 PDF Abstract BibTeX arXiv:2507.22089

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Parameter Continuation Methods for the Optimization of Deep Neural Networks

2019-12-16 · 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) 2019 12 · Harsh Nilesh Pathank, Randy Clinton Paffenroth

There are many extant methods for approximating the solutions of non-convex optimization problems arising in deep neural networks, including stochastic gradient descent, RMSProp, AdaGrad, and ADAM. In this paper, we prop…

Mollifying Networks

2016-08-17 · Caglar Gulcehre, Marcin Moczulski, Francesco Visin, Yoshua Bengio

The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can involve pathological landscapes such as…

Continuation methods as a tool for parameter inference in electrophysiology modeling

2025-01-13 · Matt J Owen, Gary R Mirams

Parameterizing mathematical models of biological systems often requires fitting to stable periodic data. In cardiac electrophysiology this typically requires converging to a stable action potential through long simulatio…

FANS: Fast Non-Autoregressive Sequence Generation for Item List Continuation

2023-04-02 · Qijiong Liu, Jieming Zhu, Jiahao Wu, Tiandeng Wu 외

User-curated item lists, such as video-based playlists on Youtube and book-based lists on Goodreads, have become prevalent for content sharing on online platforms. Item list continuation is proposed to model the overall …

Localized Physics-informed Gaussian Processes with Curriculum Training for Topology Optimization

2025-03-18 · Amin Yousefpour, Shirin Hosseinmardi, Xiangyu Sun, Ramin Bostanabad

We introduce a simultaneous and meshfree topology optimization (TO) framework based on physics-informed Gaussian processes (GPs). Our framework endows all design and state variables via GP priors which have a shared, mul…

Gaussian Processes