Zobrazeno 1 - 10
of 2 658
pro vyhledávání: '"Stéfan T"'
Cosmological simulations are a powerful tool to advance our understanding of galaxy formation and many simulations model key properties of real galaxies. A question that naturally arises for such simulations in light of high-quality observational dat
Externí odkaz:
http://arxiv.org/abs/2410.10606
Autor:
Pogorelyuk, Leonid, Radev, Stefan T.
We propose a new contrastive objective for learning overcomplete pixel-level features that are invariant to motion blur. Other invariances (e.g., pose, illumination, or weather) can be learned by applying the corresponding transformations on unlabele
Externí odkaz:
http://arxiv.org/abs/2410.07410
Autor:
Erbas, Ismail, Pandey, Vikas, Amarnath, Aporva, Wang, Naigang, Swaminathan, Karthik, Radev, Stefan T., Intes, Xavier
Fluorescence lifetime imaging (FLI) is an important technique for studying cellular environments and molecular interactions, but its real-time application is limited by slow data acquisition, which requires capturing large time-resolved images and co
Externí odkaz:
http://arxiv.org/abs/2410.00948
Autor:
Schmitt, Marvin, Li, Chengkun, Vehtari, Aki, Acerbi, Luigi, Bürkner, Paul-Christian, Radev, Stefan T.
Bayesian inference often faces a trade-off between computational speed and sampling accuracy. We propose an adaptive workflow that integrates rapid amortized inference with gold-standard MCMC techniques to achieve both speed and accuracy when perform
Externí odkaz:
http://arxiv.org/abs/2409.04332
Autor:
Habermann, Daniel, Schmitt, Marvin, Kühmichel, Lars, Bulling, Andreas, Radev, Stefan T., Bürkner, Paul-Christian
Multilevel models (MLMs) are a central building block of the Bayesian workflow. They enable joint, interpretable modeling of data across hierarchical levels and provide a fully probabilistic quantification of uncertainty. Despite their well-recognize
Externí odkaz:
http://arxiv.org/abs/2408.13230
Recent advances in probabilistic deep learning enable efficient amortized Bayesian inference in settings where the likelihood function is only implicitly defined by a simulation program (simulation-based inference; SBI). But how faithful is such infe
Externí odkaz:
http://arxiv.org/abs/2406.03154
The simplex projection expands the capabilities of simplex plots (also known as ternary plots) to achieve a lossless visualization of 4D compositional data on a 2D canvas. Previously, this was only possible for 3D compositional data. We demonstrate h
Externí odkaz:
http://arxiv.org/abs/2403.11141
In this work, we analyze the conditions under which information about the context of an input $X$ can improve the predictions of deep learning models in new domains. Following work in marginal transfer learning in Domain Generalization (DG), we forma
Externí odkaz:
http://arxiv.org/abs/2312.10107
Simulation-based inference (SBI) is constantly in search of more expressive algorithms for accurately inferring the parameters of complex models from noisy data. We present consistency models for neural posterior estimation (CMPE), a new free-form co
Externí odkaz:
http://arxiv.org/abs/2312.05440
Cognitive processes undergo various fluctuations and transient states across different temporal scales. Superstatistics are emerging as a flexible framework for incorporating such non-stationary dynamics into existing cognitive model classes. In this
Externí odkaz:
http://arxiv.org/abs/2401.08626