From f31ae770a1e09d05baa5bf42e3a2fb99dfac546f Mon Sep 17 00:00:00 2001 From: Aditya Tummala Date: Mon, 17 Jul 2023 13:26:52 -0700 Subject: [PATCH] Update param_est.ipynb --- examples/param_est.ipynb | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/examples/param_est.ipynb b/examples/param_est.ipynb index 696efd22..b86f5a5c 100644 --- a/examples/param_est.ipynb +++ b/examples/param_est.ipynb @@ -203,9 +203,10 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "An additional feature of the `estimate_params()` function is the tolerance feature, or `tol`. The `tol` argument forces our parameter estimation function to continue optimizing until we reach a particular error. This is important for cases where higher model precision is required.\n", + "An additional feature of the `estimate_params()` function is the tolerance feature, or `tol`. The exact function that the `tol` argument\n", + "uses is specific to the method used. For example, the `tol` argument for the `Nelder-Mead` method is the change in the best error between iterations, while the `tol` argument for the `L-BFGS-B` method is the change in the best parameter between iterations. For more information, see the [scipy.optimize.minimize](https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.minimize.html) documentation.\n", "\n", - "In our previous example, note that our total Error was roughly 6e-10 after the `estimate_params()` call. Now, let us see what happens to the parameters when we set a low tolerance and bounds to their respective keys!" + "In our previous example, note that our total Error was roughly __6e-10__ after the `estimate_params()` call. Now, let us see what happens to the parameters when we pass a tolerance of __1e-6__." ] }, {