Zobrazeno 1 - 10
of 1 311
pro vyhledávání: '"Bauer Stefan"'
Autor:
Feuerriegel, Stefan, Frauen, Dennis, Melnychuk, Valentyn, Schweisthal, Jonas, Hess, Konstantin, Curth, Alicia, Bauer, Stefan, Kilbertus, Niki, Kohane, Isaac S., van der Schaar, Mihaela
Publikováno v:
Nature Medicine, vol. 30, pp. 958-968 (2024)
Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes including efficacy and toxicity, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that it allows for estimating in
Externí odkaz:
http://arxiv.org/abs/2410.08770
Autor:
Mamaghan, Amir Mohammad Karimi, Papa, Samuele, Johansson, Karl Henrik, Bauer, Stefan, Dittadi, Andrea
Object-centric (OC) representations, which represent the state of a visual scene by modeling it as a composition of objects, have the potential to be used in various downstream tasks to achieve systematic compositional generalization and facilitate r
Externí odkaz:
http://arxiv.org/abs/2407.15589
Autor:
Mamaghan, Amir Mohammad Karimi, Tigas, Panagiotis, Johansson, Karl Henrik, Gal, Yarin, Annadani, Yashas, Bauer, Stefan
Representing uncertainty in causal discovery is a crucial component for experimental design, and more broadly, for safe and reliable causal decision making. Bayesian Causal Discovery (BCD) offers a principled approach to encapsulating this uncertaint
Externí odkaz:
http://arxiv.org/abs/2406.03209
We present Causal Amortized Active Structure Learning (CAASL), an active intervention design policy that can select interventions that are adaptive, real-time and that does not require access to the likelihood. This policy, an amortized network based
Externí odkaz:
http://arxiv.org/abs/2405.16718
Autor:
Vinuesa, Ricardo, Rabault, Jean, Azizpour, Hossein, Bauer, Stefan, Brunton, Bingni W., Elofsson, Arne, Jarlebring, Elias, Kjellstrom, Hedvig, Markidis, Stefano, Marlevi, David, Cinnella, Paola, Brunton, Steven L.
Technological advancements have substantially increased computational power and data availability, enabling the application of powerful machine-learning (ML) techniques across various fields. However, our ability to leverage ML methods for scientific
Externí odkaz:
http://arxiv.org/abs/2405.04161
Autor:
Wei, Ye, Peng, Bo, Xie, Ruiwen, Chen, Yangtao, Qin, Yu, Wen, Peng, Bauer, Stefan, Tung, Po-Yen
A tremendous range of design tasks in materials, physics, and biology can be formulated as finding the optimum of an objective function depending on many parameters without knowing its closed-form expression or the derivative. Traditional derivative-
Externí odkaz:
http://arxiv.org/abs/2404.04062
Autor:
Gupta, Tarun, Gong, Wenbo, Ma, Chao, Pawlowski, Nick, Hilmkil, Agrin, Scetbon, Meyer, Rigter, Marc, Famoti, Ade, Llorens, Ashley Juan, Gao, Jianfeng, Bauer, Stefan, Kragic, Danica, Schölkopf, Bernhard, Zhang, Cheng
Recent advances in foundation models, especially in large multi-modal models and conversational agents, have ignited interest in the potential of generally capable embodied agents. Such agents will require the ability to perform new tasks in many dif
Externí odkaz:
http://arxiv.org/abs/2402.06665
Autor:
Bauer, Stefan, Benner, Peter, Bereau, Tristan, Blum, Volker, Boley, Mario, Carbogno, Christian, Catlow, C. Richard A., Dehm, Gerhard, Eibl, Sebastian, Ernstorfer, Ralph, Fekete, Ádám, Foppa, Lucas, Fratzl, Peter, Freysoldt, Christoph, Gault, Baptiste, Ghiringhelli, Luca M., Giri, Sajal K., Gladyshev, Anton, Goyal, Pawan, Hattrick-Simpers, Jason, Kabalan, Lara, Karpov, Petr, Khorrami, Mohammad S., Koch, Christoph, Kokott, Sebastian, Kosch, Thomas, Kowalec, Igor, Kremer, Kurt, Leitherer, Andreas, Li, Yue, Liebscher, Christian H., Logsdail, Andrew J., Lu, Zhongwei, Luong, Felix, Marek, Andreas, Merz, Florian, Mianroodi, Jaber R., Neugebauer, Jörg, Pei, Zongrui, Purcell, Thomas A. R., Raabe, Dierk, Rampp, Markus, Rossi, Mariana, Rost, Jan-Michael, Saal, James, Saalmann, Ulf, Sasidhar, Kasturi Narasimha, Saxena, Alaukik, Sbailò, Luigi, Scheidgen, Markus, Schloz, Marcel, Schmidt, Daniel F., Teshuva, Simon, Trunschke, Annette, Wei, Ye, Weikum, Gerhard, Xian, R. Patrick, Yao, Yi, Yin, Junqi, Zhao, Meng, Scheffler, Matthias
Science is and always has been based on data, but the terms "data-centric" and the "4th paradigm of" materials research indicate a radical change in how information is retrieved, handled and research is performed. It signifies a transformative shift
Externí odkaz:
http://arxiv.org/abs/2402.10932
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
Learning the causes of time-series data is a fundamental task in many applications, spanning from finance to earth sciences or bio-medical applications. Common approaches for this task are based on vector auto-regression, and they do not take into ac
Externí odkaz:
http://arxiv.org/abs/2311.06012