notes

I first contacted Partha as an undergraduate student in Engineering Physics more than 10 years ago. I had developed an interest in machine learning and other areas that overlapped with his themes of research. We spoke on phone and discussed why statistics, neuroscience, computer science and physics all made sense as possible career paths, but perhaps computer science would offer the right degree of breadth and exposure for the interests I had. He talked of natural computation as a scientific phenomenon.  Little did I know at the time, this was typical of Partha. He identified himself as someone studying real scientific phenomena that lend itself to what he called  “different modes of inquiry”.  Academic boundaries therefore did not matter to him. Perhaps that is why he could make profound contributions to seemingly distinct disciplines: from language learning and evolution to automatic speech recognition to machine learning and statistics. Those who knew him well knew that he always had a thread tying many distinct areas together in rather unique and unobvious ways. In his talks, he would bring manifold learning alive with tube models of vocal tracts. He would think of language learning as a  phenomenon whose study naturally led to questions around the mathematical theory and computational mechanisms of generalization.

To have been Partha’s student is a matter of deep pride for me.  It was also a privilege — few advisors would provide the quality of time and training, freedom and guidance, knowledge and perspective as he did. A typical day would look like the following. You would step out of the grad students office in Ryerson to get a drink at the fountain in the main hall. You would then peek at Partha’s office and sense a rush of enthusiasm if the lights were on. Almost always, a knock would be welcomed with an invitation to talk. Four hours later, his blackboard would have changed symbols, several papers would have been downloaded on his desktop and some quick and some slow judgements would have been made on their contributions.  Almost certainly, you would have been asked to think about why asking the right questions is perhaps more important than successfully answering  wrong ones, and why character is the most important quality of a researcher. Fortunately, I also connected with Partha through squash. Our academic meetings would get over and often be followed by a squash game. Between games, research would continue and papers would be discussed.

Partha saw and understood things differently. He often took strong positions and was articulate about them in public. There was intense clarity in his thinking as he would slowly construct a logical argument, not dismissing any important detail and yet never losing the big picture.  Writing papers with him was an absolute pleasure. To help students begin to understand the significance of their own work and develop “taste” for important research directions is in some sense the primary role of an advisor. Partha truly excelled at this.  In hindsight, spread over six years and more,  Partha shaped me as a researcher in more ways than I can describe.

I will miss Partha’s friendship and guidance.

• University of Chicago – Obituary
• On Machine Learning and Artificial Intelligence
• Geometry in Machine Learning and other lectures
• On Language Learning, Acquisition and Evolution
• Ankan Saha, Maia Fraser,  Morgan Sonderegger, Xueyuan Zhou, Hariharan Narayanan, Irina Matveeva, Vikas Sindhwani, Xiaofei He, Misha Belkin, Sandy Kutin