Proving linear mode connectivity of neural networks via optimal transport

D Ferbach, B Goujaud, G Gidel… - International …, 2024 - proceedings.mlr.press
The energy landscape of high-dimensional non-convex optimization problems is crucial to
understanding the effectiveness of modern deep neural network architectures. Recent works …

On the opportunities of green computing: A survey

Y Zhou, X Lin, X Zhang, M Wang, G Jiang, H Lu… - arXiv preprint arXiv …, 2023 - arxiv.org
Artificial Intelligence (AI) has achieved significant advancements in technology and research
with the development over several decades, and is widely used in many areas including …

A survey of lottery ticket hypothesis

B Liu, Z Zhang, P He, Z Wang, Y Xiao, R Ye… - arXiv preprint arXiv …, 2024 - arxiv.org
The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a
highly sparse subnetwork (ie, winning tickets) that can achieve even better performance …

Polynomially over-parameterized convolutional neural networks contain structured strong winning lottery tickets

A Da Cunha, F d'Amore - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Abstract The Strong Lottery Ticket Hypothesis (SLTH) states that randomly-initialised neural
networks likely contain subnetworks that perform well without any training. Although …

On the multidimensional random subset sum problem

L Becchetti, ACW da Cunha, A Clementi… - arXiv preprint arXiv …, 2022 - arxiv.org
In the Random Subset Sum Problem, given $ n $ iid random variables $ X_1,..., X_n $, we
wish to approximate any point $ z\in [-1, 1] $ as the sum of a suitable subset $ X_ {i_1 (z)} …

Successfully applying lottery ticket hypothesis to diffusion model

C Jiang, B Hui, B Liu, D Yan - arXiv preprint arXiv:2310.18823, 2023 - arxiv.org
Despite the success of diffusion models, the training and inference of diffusion models are
notoriously expensive due to the long chain of the reverse process. In parallel, the Lottery …

Strong Lottery Ticket Hypothesis with –perturbation

Z Xiong, F Liao, A Kyrillidis - International Conference on …, 2023 - proceedings.mlr.press
Abstract The strong Lottery Ticket Hypothesis (LTH)(Ramanujan et al., 2019; Zhou et al.,
2019) claims the existence of a subnetwork in a sufficiently large, randomly initialized neural …

Cyclic Sparse Training: Is it Enough?

A Gadhikar, SH Nelaturu, R Burkholz - arXiv preprint arXiv:2406.02773, 2024 - arxiv.org
The success of iterative pruning methods in achieving state-of-the-art sparse networks has
largely been attributed to improved mask identification and an implicit regularization induced …

Partial Search in a Frozen Network is Enough to Find a Strong Lottery Ticket

H Otsuka, D Chijiwa, ÁL García-Arias, Y Okoshi… - arXiv preprint arXiv …, 2024 - arxiv.org
Randomly initialized dense networks contain subnetworks that achieve high accuracy
without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al.(2023) …

Considering Layerwise Importance in the Lottery Ticket Hypothesis

B Vandersmissen, J Oramas - arXiv preprint arXiv:2302.11244, 2023 - arxiv.org
The Lottery Ticket Hypothesis (LTH) showed that by iteratively training a model, removing
connections with the lowest global weight magnitude and rewinding the remaining …