Embedded Files
What happens if someone uses stochastic gradient descent with batch size one in a simple linear regression problem? Does the estimator converge to the OLS estimator which uses the full data?
Using deep neural nets to solve an optimal control problem. Example from Recursive Macroeconomic Theory by Lars Ljungqvist and Tom Sargent, 3rd edition, Exercise 5.11
Ill-posed problems and over-parameterization : Applications in Economics (soon)
Ill-posed problems and over-parameterization : Applications in Economics (soon)
Stochastic gradient descent is biased toward a specific class of solutions.
Symmetry: Dimensionality reduction and generalization (Working on it)
Symmetry: Dimensionality reduction and generalization (Working on it)
Symmetry as an a priori information can lead to extensive dimensionality reduction (alleviation of curse of dimensionality) and extreme generalization power. I provide two examples: rotation and permutation invariance
Concentration of measures: A simple observation
Concentration of measures: A simple observation
"It is of course impossible to even think the word Gaussian without immediately mentioning the most important property of Gaussian processes, that is concentration of measure." M. Talagrand
The code is written as a gift for a great teacher and mentor
Google Sites
Report abuse