In: Mathematical Geosciences, 2015, vol. 47, no. 7, p. 771-789
|
In: Statistics and Computing, 2015, vol. 25, no. 1, p. 47-63
|
In: Entropy, 2019, vol. 21, no. 8, p. 758
Variational inference with a factorized Gaussian posterior estimate is a widely-used approach for learning parameters and hidden variables. Empirically, a regularizing effect can be observed that is poorly understood. In this work, we show how mean field inference improves generalization by limiting mutual information between learned parameters and the data through noise. We quantify a...
|
In: Computational Statistics, 2014, vol. 29, no. 3-4, p. 407-430
|
In: Mathematische Zeitschrift, 2014, vol. 276, no. 3-4, p. 635-654
|
In: Physical Review B, 2018, vol. 98, no. 23, p. 235423
The only unequivocal known criterion for single-parameter scaling Anderson localization relies on the knowledge of the full conductance statistics. To date, theoretical studies have been restricted to model systems with symmetric scatterers, hence lacking universality. We present an in-depth statistical study of conductance distributions P(g), in disordered ‘micrometer-long’ carbon...
|
In: Optical and Quantum Electronics, 2011, vol. 42, no. 11-13, p. 667-677
|
In: Computational Economics, 2007, vol. 29, no. 3-4, p. 313-331
|
In: General Relativity and Gravitation, 2008, vol. 40, no. 2-3, p. 301-328
|
In: Oecologia, 2011, vol. 166, no. 4, p. 961-971
|