paper-with-me

홈 › Papers

Is the Lottery Fair? Evaluating Winning Tickets Across Demographics

2021-08-01 · Findings (ACL) 2021 8 · Victor Petrén Bach Hansen, Anders Søgaard
📄 PDF Abstract BibTeX

Code (1)

vpetren/fairness_lottery 공식 구현 pytorch

Similar Papers 제목 키워드 기반

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers

2019-06-06 · NeurIPS 2019 12 · Ari S. Morcos, Haonan Yu, Michela Paganini, Yuandong Tian

The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately. Unfortunately, finding these "winning …

All

Winning Lottery Tickets in Deep Generative Models

2020-10-05 · Neha Mukund Kalibhat, Yogesh Balaji, Soheil Feizi

The lottery ticket hypothesis suggests that sparse, sub-networks of a given neural network, if initialized properly, can be trained to reach comparable or even better performance to that of the original network. Prior wo…

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models

2024-02-05 · Fei Yuan, Chang Ma, Shuai Yuan, Qiushi Sun 외

The lottery ticket hypothesis posits the existence of ``winning tickets'' within a randomly initialized neural network. Do winning tickets exist for LLMs in fine-tuning scenarios? How can we find such winning tickets? In…

Translation

When Layers Play the Lottery, all Tickets Win at Initialization

2023-01-25 · Artur Jordao, George Correa de Araujo, Helena de Almeida Maia, Helio Pedrini

Pruning is a standard technique for reducing the computational cost of deep networks. Many advances in pruning leverage concepts from the Lottery Ticket Hypothesis (LTH). LTH reveals that inside a trained dense network e…

All

The Sooner The Better: Investigating Structure of Early Winning Lottery Tickets

2019-09-25 · Shihui Yin, Kyu-Hyoun Kim, Jinwook Oh, Naigang Wang 외

The recent success of the lottery ticket hypothesis by Frankle & Carbin (2018) suggests that small, sparsified neural networks can be trained as long as the network is initialized properly. Several follow-up discussions …

Memorization