paper-with-me

Papers

Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model

2022-05-24 · BigScience (ACL) 2022 5 · Sosuke Kobayashi, Shun Kiyono, Jun Suzuki, Kentaro Inui

Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble members. This paper proposes Multi-Ticket Ensemble, which finetunes different subnetworks of a single pretrained model and ensembles them. We empirically demonstrated that winning-ticket subnetworks produced more diverse predictions than dense networks, and their ensemble outperformed the standard ensemble on some tasks.

📄 PDF Abstract BibTeX arXiv:2205.11833

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost

2022-08-23 · Lu Yin, Shiwei Liu, Meng Fang, Tianjin Huang 외

Lottery tickets (LTs) is able to discover accurate and sparse subnetworks that could be trained in isolation to match the performance of dense networks. Ensemble, in parallel, is one of the oldest time-proven tricks in m…

Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training

2023-09-21

The recently developed sparse network training methods, such as Lottery Ticket Hypothesis (LTH) and its variants, have shown impressive learning capacity by finding sparse sub-networks from a dense one. While these metho…

Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training

2023-09-21 · NeurIPS 2023 11

The recently developed sparse network training methods, such as Lottery Ticket Hypothesis (LTH) and its variants, have shown impressive learning capacity by finding sparse sub-networks from a dense one. While these metho…

A Neural Scaling Law from Lottery Ticket Ensembling

2023-10-03 · Ziming Liu, Max Tegmark

Neural scaling laws (NSL) refer to the phenomenon where model performance improves with scale. Sharma & Kaplan analyzed NSL using approximation theory and predict that MSE losses decay as $N^{-\alpha}$, $\alpha=4/d$, whe…

Attribute

Convolutional and Residual Networks Provably Contain Lottery Tickets

2022-05-04 · Rebekka Burkholz

The Lottery Ticket Hypothesis continues to have a profound practical impact on the quest for small scale deep neural networks that solve modern deep learning tasks at competitive performance. These lottery tickets are id…