My advisor in graduate school was Ioannis Sgouralis : a man who happened to be a polymath of sorts; very knowledgeable, very thorough, and even more humble.
He could ease his way from the most idiosyncratic discourses on Ribosomes and how they function in protein synthesis, to the most critical proofs of some mathematical lemma required to formulate a simpler computational path to operate his MCMC sampler.
Ioannis, by trade, is a Mathematician, an Applied one. But you couldn’t really box him. His wide range of collaborations attested to a man who is interested in solving problems, and he would devote time to learn much of the requisite background to discuss freely about the projects he cared about.
As a student, I naturally desired to emulate him at first. Read wide, and perhaps develop a great knowledge base about the world.
I began, but quickly realized that it would take at least a decade of deliberate, continuous practice to measure up to any significant level. For something immediate though, I learned from Ioannis that the generalist mathematician who is interested in solving serious problems must possess a bag of ever-expanding high-quality tools and be willing to learn as much about the problem as perhaps the domain experts.
I am not yet half the scientist that Ioannis is, but I have continued to apply his ethos to my journey to become a very valuable data scientist.
For the initial installments of posts on this blog, I will be sharing some of the tools and perspectives I have learned and continue to learn about how we approach data-driven problems. Some posts will have more technical details than others, some will provide commentaries on new projects I will be applying these tools to in real time, but ultimately, I hope it makes for worthwhile reading.
See you in the next post!