Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Kuebler, Jonas"'
Autor:
Park, Youngsuk, Budhathoki, Kailash, Chen, Liangfu, Kübler, Jonas, Huang, Jiaji, Kleindessner, Matthäus, Huan, Jun, Cevher, Volkan, Wang, Yida, Karypis, George
Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new applications
Externí odkaz:
http://arxiv.org/abs/2407.09111
In aggregated variables the impact of interventions is typically ill-defined because different micro-realizations of the same macro-intervention can result in different changes of downstream macro-variables. We show that this ill-definedness of causa
Externí odkaz:
http://arxiv.org/abs/2304.11625
Multi-armed bandits are one of the theoretical pillars of reinforcement learning. Recently, the investigation of quantum algorithms for multi-armed bandit problems was started, and it was found that a quadratic speed-up (in query complexity) is possi
Externí odkaz:
http://arxiv.org/abs/2301.08544
Two-sample tests are important in statistics and machine learning, both as tools for scientific discovery as well as to detect distribution shifts. This led to the development of many sophisticated test procedures going beyond the standard supervised
Externí odkaz:
http://arxiv.org/abs/2206.08843
Autor:
Gresele, Luigi, von Kügelgen, Julius, Kübler, Jonas M., Kirschbaum, Elke, Schölkopf, Bernhard, Janzing, Dominik
Publikováno v:
International Conference on Machine Learning (ICML 2022), 7793-7824
We introduce an approach to counterfactual inference based on merging information from multiple datasets. We consider a causal reformulation of the statistical marginal problem: given a collection of marginal structural causal models (SCMs) over dist
Externí odkaz:
http://arxiv.org/abs/2202.01300
Autor:
Jerbi, Sofiene, Fiderer, Lukas J., Nautrup, Hendrik Poulsen, Kübler, Jonas M., Briegel, Hans J., Dunjko, Vedran
Publikováno v:
Nature Communications 14, 517 (2023)
Machine learning algorithms based on parametrized quantum circuits are prime candidates for near-term applications on noisy quantum computers. In this direction, various types of quantum machine learning models have been introduced and studied extens
Externí odkaz:
http://arxiv.org/abs/2110.13162
Publikováno v:
Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
It has been hypothesized that quantum computers may lend themselves well to applications in machine learning. In the present work, we analyze function classes defined via quantum kernels. Quantum computers offer the possibility to efficiently compute
Externí odkaz:
http://arxiv.org/abs/2106.03747
The Maximum Mean Discrepancy (MMD) has been the state-of-the-art nonparametric test for tackling the two-sample problem. Its statistic is given by the difference in expectations of the witness function, a real-valued function defined as a weighted su
Externí odkaz:
http://arxiv.org/abs/2102.05573
Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data splitting to obtain the most powerful test statistics. While data splitt
Externí odkaz:
http://arxiv.org/abs/2006.02286
We propose a new family of specification tests called kernel conditional moment (KCM) tests. Our tests are built on a novel representation of conditional moment restrictions in a reproducing kernel Hilbert space (RKHS) called conditional moment embed
Externí odkaz:
http://arxiv.org/abs/2002.09225