Zobrazeno 1 - 10
of 3 051
pro vyhledávání: '"Huszar, A."'
Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the outer-loop app
Externí odkaz:
http://arxiv.org/abs/2411.00666
LLMs show remarkable emergent abilities, such as inferring concepts from presumably out-of-distribution prompts, known as in-context learning. Though this success is often attributed to the Transformer architecture, our systematic understanding is li
Externí odkaz:
http://arxiv.org/abs/2409.13728
Autor:
Bonnet, Édouard, Huszár, Kristóf
Building on Whitney's classical method of triangulating smooth manifolds, we show that every compact $d$-dimensional smooth manifold admits a triangulation with dual graph of twin-width at most $d^{O(d)}$. In particular, it follows that every compact
Externí odkaz:
http://arxiv.org/abs/2407.10174
Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather independently. We observe that several methods in both representation and ca
Externí odkaz:
http://arxiv.org/abs/2406.14302
We study causal effect estimation in a setting where the data are not i.i.d. (independent and identically distributed). We focus on exchangeable data satisfying an assumption of independent causal mechanisms. Traditional causal effect estimation fram
Externí odkaz:
http://arxiv.org/abs/2405.18836
Autor:
Guo, Siyuan, Didolkar, Aniket, Ke, Nan Rosemary, Goyal, Anirudh, Huszár, Ferenc, Schölkopf, Bernhard
We are beginning to see progress in language model assisted scientific discovery. Motivated by the use of LLMs as a general scientific assistant, this paper assesses the domain knowledge of LLMs through its understanding of different mathematical ski
Externí odkaz:
http://arxiv.org/abs/2405.15485
Autor:
Lee, Royson, Fernandez-Marques, Javier, Hu, Shell Xu, Li, Da, Laskaridis, Stefanos, Dudziak, Łukasz, Hospedales, Timothy, Huszár, Ferenc, Lane, Nicholas D.
Federated learning (FL) has enabled distributed learning of a model across multiple clients in a privacy-preserving manner. One of the main challenges of FL is to accommodate clients with varying hardware capacities; clients have differing compute an
Externí odkaz:
http://arxiv.org/abs/2405.14791
Autor:
Reizinger, Patrik, Ujváry, Szilvia, Mészáros, Anna, Kerekes, Anna, Brendel, Wieland, Huszár, Ferenc
The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this progress: the study of overparametrized models in the interpolation regi
Externí odkaz:
http://arxiv.org/abs/2405.01964
Autor:
Lee, Royson, Kim, Minyoung, Li, Da, Qiu, Xinchi, Hospedales, Timothy, Huszár, Ferenc, Lane, Nicholas D.
Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those common models to the specifics of each client's local data distribution. H
Externí odkaz:
http://arxiv.org/abs/2310.02420
Autor:
Azim Huszar, BSc, Jason Thomas, BMBS, Edris Adel, BMBS, Charles Timon, MRCS, Aidan O’Sullivan, PhD, Leonard O’Sullivan, PhD, John Tristan Cassidy, FRCS
Publikováno v:
JSES Reviews, Reports, and Techniques, Vol 4, Iss 4, Pp 854-858 (2024)
Externí odkaz:
https://doaj.org/article/607e681f9f8041d7b50aad3ca113d9aa
