Zobrazeno 1 - 10
of 1 629
pro vyhledávání: '"Attias P"'
We present novel reductions from sample compression schemes in multiclass classification, regression, and adversarially robust learning settings to binary sample compression schemes. Assuming we have a compression scheme for binary classes of size $f
Externí odkaz:
http://arxiv.org/abs/2410.13012
We study the fundamental problem of sequential probability assignment, also known as online learning with logarithmic loss, with respect to an arbitrary, possibly nonparametric hypothesis class. Our goal is to obtain a complexity measure for the hypo
Externí odkaz:
http://arxiv.org/abs/2410.03849
Convolutional Neural Networks (CNNs) excel in many visual tasks, but they tend to be sensitive to slight input perturbations that are imperceptible to the human eye, often resulting in task failures. Recent studies indicate that training CNNs with re
Externí odkaz:
http://arxiv.org/abs/2410.03952
Autor:
Saba, Andrew, Adetunji, Aderotimi, Johnson, Adam, Kothari, Aadi, Sivaprakasam, Matthew, Spisak, Joshua, Bharatia, Prem, Chauhan, Arjun, Duff Jr., Brendan, Gasparro, Noah, King, Charles, Larkin, Ryan, Mao, Brian, Nye, Micah, Parashar, Anjali, Attias, Joseph, Balciunas, Aurimas, Brown, Austin, Chang, Chris, Gao, Ming, Heredia, Cindy, Keats, Andrew, Lavariega, Jose, Muckelroy III, William, Slavescu, Andre, Stathas, Nickolas, Suvarna, Nayana, Zhang, Chuan Tian, Scherer, Sebastian, Ramanan, Deva
Publikováno v:
Field Robotics Volume 4 (2024) 1-45
Autonomous motorsports aim to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their handling limits in multi-agent scenarios at extremely high ($\geq 150mph$
Externí odkaz:
http://arxiv.org/abs/2408.15425
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
Autor:
Salierno, Giulio, Bertè, Rosamaria, Attias, Luca, Morrone, Carla, Pettazzoni, Dario, Battisti, Daniela
Recent advances in Natural Language Processing have demonstrated the effectiveness of pretrained language models like BERT for a variety of downstream tasks. We present GiusBERTo, the first BERT-based model specialized for anonymizing personal data i
Externí odkaz:
http://arxiv.org/abs/2406.15032
Publikováno v:
Phys. Rev. B 110, 094425 (2024)
We study the anomalous Hall effect arising from the altermagnetic order and spin-orbit interaction in doped FeSb$_2$. To investigate the anomalous transport, we have constructed a tight-binding model of FeSb$_2$. We separately considered the constrai
Externí odkaz:
http://arxiv.org/abs/2402.12115
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
Publikováno v:
Phys. Rev. B 110, 014521 (2024)
We investigate the planar Hall effect (PHE) in two-dimensional (2D) superconductors with spin-orbit interactions, where transport anisotropy is induced by an in-plane magnetic field. While PHE typically arises from the breaking of basal mirror symmet
Externí odkaz:
http://arxiv.org/abs/2312.15688
In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of the fat shattering dimension for
Externí odkaz:
http://arxiv.org/abs/2307.03848