Zobrazeno 1 - 10
of 2 727
pro vyhledávání: '"Jesson A"'
This work is about estimating when a conditional generative model (CGM) can solve an in-context learning (ICL) problem. An in-context learning (ICL) problem comprises a CGM, a dataset, and a prediction task. The CGM could be a multi-modal foundation
Externí odkaz:
http://arxiv.org/abs/2412.06033
Autor:
Shi, Claudia, Beltran-Velez, Nicolas, Nazaret, Achille, Zheng, Carolina, Garriga-Alonso, Adrià, Jesson, Andrew, Makar, Maggie, Blei, David M.
Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily executed by small subnetworks within the LLM, known as circuits. But ho
Externí odkaz:
http://arxiv.org/abs/2410.13032
Autor:
Jesson, Andrew, Jiang, Yiding
We demonstrate that recent advances in reinforcement learning (RL) combined with simple architectural changes significantly improves generalization on the ProcGen benchmark. These changes are frame stacking, replacing 2D convolutional layers with 3D
Externí odkaz:
http://arxiv.org/abs/2410.10905
Autor:
Jesson, Andrew, Beltran-Velez, Nicolas, Chu, Quentin, Karlekar, Sweta, Kossen, Jannik, Gal, Yarin, Cunningham, John P., Blei, David
This paper presents a method for estimating the hallucination rate for in-context learning (ICL) with generative AI. In ICL, a conditional generative model (CGM) is prompted with a dataset and a prediction question and asked to generate a response. O
Externí odkaz:
http://arxiv.org/abs/2406.07457
Autor:
Lyle, Clare, Mehrjou, Arash, Notin, Pascal, Jesson, Andrew, Bauer, Stefan, Gal, Yarin, Schwab, Patrick
Publikováno v:
International Conference on Machine Learning, 2023
The discovery of therapeutics to treat genetically-driven pathologies relies on identifying genes involved in the underlying disease mechanisms. Existing approaches search over the billions of potential interventions to maximize the expected influenc
Externí odkaz:
http://arxiv.org/abs/2312.04064
Autor:
Clément Tisseron, Joël Djaha, Désiré Lucien Dahourou, Kouakou Kouadio, Patricia Nindjin, Marie-Sylvie N’Gbeche, Corinne Moh, François Eboua, Belinda Bouah, Eulalie Kanga, Muhammad Homayoon Manochehr, Marie-Hélène Doucet, Philippe Msellati, Julie Jesson, Valériane Leroy, for the IeDEA and OPTIMISE West-African Collaborations
Publikováno v:
Reproductive Health, Vol 21, Iss 1, Pp 1-11 (2024)
Abstract Introduction Adolescents face unique challenges in accessing appropriate information and services regarding sexuality and reproductive health (SRH). This poor access can lead to sexual behaviours that could put them at risk of unintended pre
Externí odkaz:
https://doaj.org/article/ed4d9c1086e142069559405436ccb5e8
Autor:
Malik, Shreshth A., Lahlou, Salem, Jesson, Andrew, Jain, Moksh, Malkin, Nikolay, Deleu, Tristan, Bengio, Yoshua, Gal, Yarin
We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward. With an appropriate reward function to quantify the utility of acquiring a batch
Externí odkaz:
http://arxiv.org/abs/2306.15058
Autor:
Jesson, Andrew, Lu, Chris, Gupta, Gunshi, Beltran-Velez, Nicolas, Filos, Angelos, Foerster, Jakob Nicolaus, Gal, Yarin
This paper proposes a step toward approximate Bayesian inference in on-policy actor-critic deep reinforcement learning. It is implemented through three changes to the Asynchronous Advantage Actor-Critic (A3C) algorithm: (1) applying a ReLU function t
Externí odkaz:
http://arxiv.org/abs/2306.01460
Publikováno v:
PMLR 202 (2023) 26599-26618
Estimating heterogeneous treatment effects from observational data is a crucial task across many fields, helping policy and decision-makers take better actions. There has been recent progress on robust and efficient methods for estimating the conditi
Externí odkaz:
http://arxiv.org/abs/2304.10577
Autor:
Kalysha Closson, Erica Dong, Bongiwe Zulu, Janan J. Dietrich, Campion Zharima, Julie Jesson, Tatiana Pakhomova, Mags Beksinska, Angela Kaida
Publikováno v:
BMC Public Health, Vol 24, Iss 1, Pp 1-9 (2024)
Abstract Background In South Africa, pervasive age and gender inequities have been exacerbated by the COVID-19 pandemic and public health response. We aimed to explore experiences of the COVID-19 pandemic among youth in eThekwini district, South Afri
Externí odkaz:
https://doaj.org/article/ddd2b0c7297c4188a7fffe81508f9d23