Reproduction of "On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime"

• Fig 2: experiments/grokking/mnist-grokking-best.ipynb
• Fig 3: experiments/gauss_newton/ex_1.ipynb
• Fig 4: experiments/pinns/make_plots_new.ipynb
• Fig 5: experiments/grokking/modulo_example.ipynb
• Fig 6: experiments/grokking/grokking_polynomial.ipynb
• Fig 7: experiments/grokking/mnist-grokking-best.ipynb