Zobrazeno 1 - 10
of 511
pro vyhledávání: '"A. Waiss"'
We present skwdro, a Python library for training robust machine learning models. The library is based on distributionally robust optimization using optimal transport distances. For ease of use, it features both scikit-learn compatible estimators for
Externí odkaz:
http://arxiv.org/abs/2410.21231
In this paper, we examine the long-run distribution of stochastic gradient descent (SGD) in general, non-convex problems. Specifically, we seek to understand which regions of the problem's state space are more likely to be visited by SGD, and by how
Externí odkaz:
http://arxiv.org/abs/2406.09241
Stochastic gradient methods are among the most important algorithms in training machine learning problems. While classical assumptions such as strong convexity allow a simple analysis they are rarely satisfied in applications. In recent years, global
Externí odkaz:
http://arxiv.org/abs/2405.13592
Exact Bayesian inference on state-space models~(SSM) is in general untractable, and unfortunately, basic Sequential Monte Carlo~(SMC) methods do not yield correct approximations for complex models. In this paper, we propose a mixed inference algorith
Externí odkaz:
http://arxiv.org/abs/2312.09860
Publikováno v:
37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023), Dec 2023, New Orleans, United States
Wasserstein distributionally robust estimators have emerged as powerful models for prediction and decision-making under uncertainty. These estimators provide attractive generalization guarantees: the robust objective obtained from the training distri
Externí odkaz:
http://arxiv.org/abs/2305.17076
We examine the last-iterate convergence rate of Bregman proximal methods - from mirror descent to mirror-prox and its optimistic variants - as a function of the local geometry induced by the prox-mapping defining the method. For generality, we focus
Externí odkaz:
http://arxiv.org/abs/2211.08043
Autor:
Alexander Tinchon, Joana Brait, Sascha Klee, Uwe Graichen, Christian Baumgartner, Oliver Friedrich, Elisabeth Freydl, Stefan Oberndorfer, Walter Struhal, Barbara Hain, Christoph Waiß, Dagmar Stoiber
Publikováno v:
Frontiers in Pharmacology, Vol 15 (2024)
IntroductionAnti-Xa serves as a clinical surrogate for assessing the efficacy and bleeding risk in patients treated with enoxaparin for thromboembolic events. Evidence from the literature and empirical observations suggest that patients are underdose
Externí odkaz:
https://doaj.org/article/ae74c80d88db47048c176713e9c630b2
Autor:
Mark Contreras Waiss
Publikováno v:
Antec, Vol 8, Iss 1 (2024)
Externí odkaz:
https://doaj.org/article/8afaaa0300ec4c0483cd8bfaaf84c1b5
Optimal transport has recently proved to be a useful tool in various machine learning applications needing comparisons of probability measures. Among these, applications of distributionally robust optimization naturally involve Wasserstein distances
Externí odkaz:
http://arxiv.org/abs/2205.08826
Autor:
Christoph Waiß, Barbara Ströbele, Uwe Graichen, Sascha Klee, Joshua Gartlehner, Estelle Sonntagbauer, Stephanie Hirschbichler, Alexander Tinchon, Emrah Kacar, Bianca Wuchty, Bianka Novotna, Zofia Kühn, Johann Sellner, Walter Struhal, Christian Bancher, Peter Schnider, Susanne Asenbaum-Nan, Stefan Oberndorfer
Publikováno v:
Journal of Central Nervous System Disease, Vol 16 (2024)
Background ‘Definite Neuroborreliosis (NB)’ is diagnosed with the presence of NB-specific symptoms, cerebrospinal fluid (CSF) pleocytosis and an elevated Borrelia Burgdorferi antibody index. However, some diagnostic uncertainties exist. The B-cel
Externí odkaz:
https://doaj.org/article/fe56ba47bda2446cbfad82887e73c390