Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Huang, Daolang"'
Many critical decisions, such as personalized medical diagnoses and product pricing, are made based on insights gained from designing, observing, and analyzing a series of experiments. This highlights the crucial role of experimental design, which go
Externí odkaz:
http://arxiv.org/abs/2411.02064
Amortized meta-learning methods based on pre-training have propelled fields like natural language processing and vision. Transformer-based neural processes and their variants are leading models for probabilistic meta-learning with a tractable objecti
Externí odkaz:
http://arxiv.org/abs/2410.15320
Simulation-based inference (SBI) is the preferred framework for estimating parameters of intractable models in science and engineering. A significant challenge in this context is the large computational cost of simulating data from complex models, an
Externí odkaz:
http://arxiv.org/abs/2410.07930
Autor:
Huang, Daolang, Haussmann, Manuel, Remes, Ulpu, John, ST, Clarté, Grégoire, Luck, Kevin Sebastian, Kaski, Samuel, Acerbi, Luigi
Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as in spatio-temporal mode
Externí odkaz:
http://arxiv.org/abs/2306.10915
Simulation-based inference (SBI) methods such as approximate Bayesian computation (ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating statistics to infer parameters of intractable likelihood models. However, such met
Externí odkaz:
http://arxiv.org/abs/2305.15871
Bayesian optimization (BO) is a well-established method to optimize black-box functions whose direct evaluations are costly. In this paper, we tackle the problem of incorporating expert knowledge into BO, with the goal of further accelerating the opt
Externí odkaz:
http://arxiv.org/abs/2208.08742