Zobrazeno 1 - 10
of 1 332
pro vyhledávání: '"Roy, P M"'
Social dilemmas where the good of a group is at odds with individual interests are usually considered as static -- the dilemma does not change over time. In the COVID-19 pandemic, social dilemmas occurred in the mitigation of epidemic spread: Should
Externí odkaz:
http://arxiv.org/abs/2410.22917
Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all tasks. When applied to all but the last layer of weights, existing me
Externí odkaz:
http://arxiv.org/abs/2410.12766
We study the fundamental problem of sequential probability assignment, also known as online learning with logarithmic loss, with respect to an arbitrary, possibly nonparametric hypothesis class. Our goal is to obtain a complexity measure for the hypo
Externí odkaz:
http://arxiv.org/abs/2410.03849
In this work, we investigate the problem of adapting to the presence or absence of causal structure in multi-armed bandit problems. In addition to the usual reward signal, we assume the learner has access to additional variables, observed in each rou
Externí odkaz:
http://arxiv.org/abs/2407.00950
We introduce LatentTimePFN (LaT-PFN), a foundational Time Series model with a strong embedding space that enables zero-shot forecasting. To achieve this, we perform in-context learning in latent space utilizing a novel integration of the Prior-data F
Externí odkaz:
http://arxiv.org/abs/2405.10093
Autor:
Sharma, Ekansh, Kwok, Devin, Denton, Tom, Roy, Daniel M., Rolnick, David, Dziugaite, Gintare Karolina
Neural networks typically exhibit permutation symmetries which contribute to the non-convexity of the networks' loss landscapes, since linearly interpolating between two permuted versions of a trained network tends to encounter a high loss barrier. R
Externí odkaz:
http://arxiv.org/abs/2404.06498
In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). We define memorization via the information a learning algorithm reveals about its training data points. We the
Externí odkaz:
http://arxiv.org/abs/2402.09327
Autor:
Ackerman, Nathanael L., Freer, Cameron E., Kaddar, Younesse, Karwowski, Jacek, Moss, Sean K., Roy, Daniel M., Staton, Sam, Yang, Hongseok
Publikováno v:
Proc. ACM Program. Lang. 8, POPL, Article 61 (2024), pp 1819-1849
We study semantic models of probabilistic programming languages over graphs, and establish a connection to graphons from graph theory and combinatorics. We show that every well-behaved equational theory for our graph probabilistic programming languag
Externí odkaz:
http://arxiv.org/abs/2312.17127
We show the following generalizations of the de Finetti--Hewitt--Savage theorem: Given an exchangeable sequence of random elements, the sequence is conditionally i.i.d. if and only if each random element admits a regular conditional distribution give
Externí odkaz:
http://arxiv.org/abs/2312.16349
Autor:
Sudesna Chakraborty, Roy A. M. Haast, Kate M. Onuska, Prabesh Kanel, Marco A. M. Prado, Vania F. Prado, Ali R. Khan, Taylor W. Schmitz
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-16 (2024)
Abstract Cortical cholinergic projections originate from subregions of the basal forebrain (BF). To examine its organization in humans, we computed multimodal gradients of BF connectivity by combining 7 T diffusion and resting state functional MRI. M
Externí odkaz:
https://doaj.org/article/4309096a79a2481a992268a71e9788f8
