Zobrazeno 1 - 10
of 208
pro vyhledávání: '"Larsen, Brett"'
The canonical polyadic (CP) tensor decomposition decomposes a multidimensional data array into a sum of outer products of finite-dimensional vectors. Instead, we can replace some or all of the vectors with continuous functions (infinite-dimensional v
Externí odkaz:
http://arxiv.org/abs/2408.05677
Pretraining datasets for large language models (LLMs) have grown to trillions of tokens composed of large amounts of CommonCrawl (CC) web scrape along with smaller, domain-specific datasets. It is expensive to understand the impact of these domain-sp
Externí odkaz:
http://arxiv.org/abs/2406.03476
A multitude of (dis)similarity measures between neural network representations have been proposed, resulting in a fragmented research landscape. Most of these measures fall into one of two categories. First, measures such as linear regression, canoni
Externí odkaz:
http://arxiv.org/abs/2311.11436
Measuring geometric similarity between high-dimensional network representations is a topic of longstanding interest to neuroscience and deep learning. Although many methods have been proposed, only a few works have rigorously analyzed their statistic
Externí odkaz:
http://arxiv.org/abs/2310.05742
Autor:
Paul, Mansheej, Chen, Feng, Larsen, Brett W., Frankle, Jonathan, Ganguli, Surya, Dziugaite, Gintare Karolina
Modern deep learning involves training costly, highly overparameterized networks, thus motivating the search for sparser networks that can still be trained to the same accuracy as the full network (i.e. matching). Iterative magnitude pruning (IMP) is
Externí odkaz:
http://arxiv.org/abs/2210.03044
Autor:
Paul, Mansheej, Larsen, Brett W., Ganguli, Surya, Frankle, Jonathan, Dziugaite, Gintare Karolina
A striking observation about iterative magnitude pruning (IMP; Frankle et al. 2020) is that $\unicode{x2014}$ after just a few hundred steps of dense training $\unicode{x2014}$ the method can find a sparse sub-network that can be trained to the same
Externí odkaz:
http://arxiv.org/abs/2206.01278
Autor:
Zhang, Shen, Le Blanc, J.C. Yves, Larsen, Brett, Colwill, Karen, Burton, Lyle, Guna, Mircea, Gingras, Anne-Claude, Tate, Stephen
Publikováno v:
In Analytica Chimica Acta 9 October 2024 1325
Autor:
Larsen, Brett W., Kolda, Tamara G.
We consider the matrix least squares problem of the form $\| \mathbf{A} \mathbf{X}-\mathbf{B} \|_F^2$ where the design matrix $\mathbf{A} \in \mathbb{R}^{N \times r}$ is tall and skinny with $N \gg r$. We propose to create a sketched version $\| \til
Externí odkaz:
http://arxiv.org/abs/2201.10638
A variety of recent works, spanning pruning, lottery tickets, and training within random subspaces, have shown that deep neural networks can be trained using far fewer degrees of freedom than the total number of parameters. We analyze this phenomenon
Externí odkaz:
http://arxiv.org/abs/2107.05802
Autor:
Larsen, Brett W., Kolda, Tamara G.
The low-rank canonical polyadic tensor decomposition is useful in data analysis and can be computed by solving a sequence of overdetermined least squares subproblems. Motivated by consideration of sparse tensors, we propose sketching each subproblem
Externí odkaz:
http://arxiv.org/abs/2006.16438