Zobrazeno 1 - 10
of 1 000
pro vyhledávání: '"Balabanov, P. A."'
Autor:
Balabanov, Oleksandr, Linander, Hampus
Fine-tuning large language models can improve task specific performance, although a general understanding of what the fine-tuned model has learned, forgotten and how to trust its predictions is still missing. We derive principled uncertainty quantifi
Externí odkaz:
http://arxiv.org/abs/2402.12264
Treatment approaches for colorectal cancer (CRC) are highly dependent on the molecular subtype, as immunotherapy has shown efficacy in cases with microsatellite instability (MSI) but is ineffective for the microsatellite stable (MSS) subtype. There i
Externí odkaz:
http://arxiv.org/abs/2401.16131
Autor:
Melnichenko, Maksim, Balabanov, Oleg, Murray, Riley, Demmel, James, Mahoney, Michael W., Luszczek, Piotr
This paper develops and analyzes a new algorithm for QR decomposition with column pivoting (QRCP) of rectangular matrices with large row counts. The algorithm combines methods from randomized numerical linear algebra in a particularly careful way in
Externí odkaz:
http://arxiv.org/abs/2311.08316
Publikováno v:
Acta Medica Bulgarica, Vol 51, Iss s1, Pp 22-25 (2024)
Keratoplasty is one of the most common tissue transplants. However, its application in children remains a high-risk procedure. The child eyeball is smaller, the cornea and sclera are more elastic, a higher pressure on the vitreous body and often othe
Externí odkaz:
https://doaj.org/article/04fbb3935f6f40a486cc74d7362bbc84
Randomized orthogonal projection methods (ROPMs) can be used to speed up the computation of Krylov subspace methods in various contexts. Through a theoretical and numerical investigation, we establish that these methods produce quasi-optimal approxim
Externí odkaz:
http://arxiv.org/abs/2302.07466
Publikováno v:
CVPR (2023) 13701-13711
We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochastic ensembles are formulated as families of distributions and trained to approxim
Externí odkaz:
http://arxiv.org/abs/2212.08123
Autor:
Laura Volta, Renier Myburgh, Mara Hofstetter, Christian Koch, Jonathan D. Kiefer, Celeste Gobbi, Francesco Manfredi, Kathrin Zimmermann, Philipp Kaufmann, Serena Fazio, Christian Pellegrino, Norman F. Russkamp, Danielle Villars, Mattia Matasci, Monique Maurer, Jan Mueller, Florin Schneiter, Paul Büschl, Niclas Harrer, Jacqueline Mock, Stefan Balabanov, César Nombela‐Arrieta, Timm Schroeder, Dario Neri, Markus G. Manz
Publikováno v:
HemaSphere, Vol 8, Iss 11, Pp n/a-n/a (2024)
Abstract Acute myeloid leukemia (AML) derives from hematopoietic stem and progenitor cells (HSPCs). To date, no AML‐exclusive, non‐HSPC‐expressed cell‐surface target molecules for AML selective immunotherapy have been identified. Therefore, t
Externí odkaz:
https://doaj.org/article/f01601fd49bb490c81391fc86db051b9
Publikováno v:
Machine Learning: Science and Technology 4 (2023) 045032
Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output. By looking at these posterior distributions, one can separate the origin of uncertainty into alea
Externí odkaz:
http://arxiv.org/abs/2211.14605
Publikováno v:
Proceedings of the International Conference on Machine Learning, pp. 1564-1576. PMLR, 2023
This article introduces a novel structured random matrix composed blockwise from subsampled randomized Hadamard transforms (SRHTs). The block SRHT is expected to outperform well-known dimension reduction maps, including SRHT and Gaussian matrices, on
Externí odkaz:
http://arxiv.org/abs/2210.11295
Autor:
Balabanov, Oleg
This article proposes and analyzes several variants of the randomized Cholesky QR factorization of a matrix $X$. Instead of computing the R factor from $X^T X$, as is done by standard methods, we obtain it from a small, efficiently computable random
Externí odkaz:
http://arxiv.org/abs/2210.09953