Alpha-Stable Distribution
The limiting distribution of the generalized central limit theorem, with tails that decay according to a power law, capable of characterizing heavy-tailed phenomena in which extreme events occur frequently. When alpha equals 2, it reduces to the Gaussian distribution.
Timeline (last 90 days)
StochLOB introduces two non-Gaussian noise schemes: compound Poisson variance mixture (jump-Lévy noise) and truncated α-stable noise (positive-stable Gaussian scale mixture).
Since the α-stable distribution has infinite variance, using it directly for neural network training would cause gradient explosion, so a truncated version is often adopted in practical applications.
All Facts (2)
StochLOB introduces two non-Gaussian noise schemes: compound Poisson variance mixture (jump-Lévy noise) and truncated α-stable noise (positive-stable Gaussian scale mixture).
50%UnverifiedSince the α-stable distribution has infinite variance, using it directly for neural network training would cause gradient explosion, so a truncated version is often adopted in practical applications.
50%