John Stachurski
John Stachurski
As suggested by Serge. Use data on cotton exports from Benin? This could be a lecture on how to estimate a Markov chain using ML, with cotton output/exports as the...
Take this lecture and focus on simulation https://python.quantecon.org/wealth_dynamics.html This lecture should go after #14 , so there is no need to explain what the Lorenz curve and Gini coefficient are....
The example in the DP text could be suitable. Complicated theory could be replaced by a simple backwards induction argument in a finite horizon setting.
The code to be converted to JAX is here: https://github.com/QuantEcon/book-dp1/blob/main/source_code_py/markov_js.py https://github.com/QuantEcon/book-dp1/blob/main/source_code_py/markov_js_with_sep.py These can be combined into one lecture, with the second set of code as an exercise. Background is in...
In this lecture, when we do the timings, we do not use `block_until_ready` and we don't run twice to eliminate compile time. https://jax.quantecon.org/opt_savings_1.html I think this is probably true in...
Right now, in the final figure, OPI is beating HPI for some values of m in the final figure of opt_savings_2 and opt_invest. Can HPI beat OPI if we loosen...
@mmcky Can you please search for this line: In line with immutability, JAX does not support inplace operations: It looks like JAX is sorting in place now. Could you please...
Tensor flow probability now works on JAX: https://www.tensorflow.org/probability/examples/TensorFlow_Probability_on_JAX It includes routines for Monte Carlo and multivariate optimization. Are there any lectures in https://python.quantecon.org and https://python-advanced.quantecon.org/intro.html that we can now bring...
Write a JAX version of the following code https://github.com/QuantEcon/book-dp1/blob/main/source_code_py/inventory_dp.py https://github.com/QuantEcon/book-dp1/blob/main/source_code_py/inventory_sdd.py This code can be combined into one lecture. The description of the model is in Section 5.3.1 and Section 6.3.3...