Partha Niyogi


Obituary on CS site (PDF), (HTML); Obituary on University news site

Misha Belkin

I first met Partha Niyogi almost exactly ten years ago when I was a graduate student in math and he had just started as a faculty in Computer Science and Statistics at the University of Chicago. Strangely, we first talked at length due to a somewhat convoluted mathematical argument in a paper on pattern recognition. I asked him some questions about the paper, and, even though the topic was new to him, he had put serious thought into it and we started regular meetings. We made significant progress and developed a line of research stemming initially just from trying to understand that one paper and to simplify one derivation. I think this was typical of Partha, showing both his intellectual curiousity and his intuition for the serendipitous; having a sense and focus for inquiries worth pursuing, no matter how remote and challenging, and bringing his unique vision to new areas. We had been working together continuously from that first meeting until he became too sick to continue. Partha had been a great mentor and a close friend for me; I am deeply in debt to him for his guidance, intellectual inspiration and friendship.

Partha had a unique, relaxed yet very intense attitude to work. He never pushed his students, yet he paid concentrated attention to the work. He was better than anyone else I know at focusing on the essential. Another characteristic feature, something which I have been trying to emulate over the years, was his ability to make deep connections between seemingly disjoint ideas, connections whose importance emerged over time. Many times, the things he saw and said turned out to be right in ways and for reasons, which were not immediately obvious or predictable at the time.

Partha had a broad range of interests both in research and outside of it. His scientific interests spanned speech recognition, machine learning, and language evolution, on which he had written a 500-page monograph. In every one of these areas he had his own vision, distinct, clear, and not afraid to challenge unexamined conventional wisdom. He was also widely read, broadly knowledgeable and curious, interested in subjects from music to economics to literature and history, and somehow being able to combine all of that with his research, family and teaching.

I owe a lot to Partha in my research, outlook and worldview; his insight and thoughtful attitude to every aspect of life have deeply influenced me. He had always supported me in difficulty, I wish I had done as much for him in his hard times...

It had been a great privilege to be Partha's student, collaborator and friend; his passing away leaves deep sadness and emptiness. But his friendship and what I learned from him will stay with me for the rest of my life.

Sandy Kutin

Partha Niyogi was my advisor, mentor, and friend. He had a wonderful way of looking at AI and finding math problems that were challenging but tractable, and that were intrinsically interesting but also had applications. He was generous with his students, both with his time and with his ideas. Most importantly to me, he gave me advice about my career and then set me free to make my own decisions.

Tomaso Poggio

Words of a friend of Partha and Parvati

Partha was supersmart, was generous, was fair, was a great friend.

But he was much more than that.

He was a real intellectual with a family tradition. He cared deeply about politics and people and most of all about science and human nature and intelligence.

He was my guide, my oracle for many questions about science and math. Among all statisticians I know, he was the one I most respect, together with David Donoho.

In our fields of machine learning and computer science he knew more than anybody else and understood better than anybody else.

A broad and deep intelligence. A mind as clear and crisp as a September day.

A most beautiful mind.

Vikas Sindhwani

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 chords. 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.

From the memorial service for Partha on October 30, 2010

Yali Amit


I first met Partha during his job interview with the Computer Science department and was immediately struck by his thoughtfulness, this quiet, soft-spoken, understated in-depth knowledge in so many fields. Not your typical flashy MIT AI character. I was very excited about recruiting him and delighted when he agreed to come to the CS department. Several months after his arrival it became clear to me that offering him a position in the Statistics Department, as well, would help create important bridges between Machine Learning--his field of research and more traditional Statistics. In the Statistics Department we all came to appreciate his special qualities, his deep insights and measured judgments, especially regarding hiring and promotion.

In our building, Eckhart Hall, the office doors are closed and locked for security reasons. In Statistics we have a curious system whereby full time faculty all carry a master key, thus saving each other the effort to get up and open the door. So when someone knocks you know it isn't faculty and its most likely a student. But students knock timidly. So whenever I heard a loud double rap--I knew it was Partha. He'd walk right in with his question of the day...

Perhaps the greatest thing about Partha was his ability to ask questions, and what is more important in scientific inquiry than coming up with good questions? Partha questioned everything, including his own work. He posed hard pointed questions. He really wanted to get to the root of things. For example in his early work in Speech Recognition he made use of Support Vector Machines, a classification method that became popular during the 90's that consisted of a modification of penalized regression with a data term more suitable for classification. But I remember Partha repeatedly wondering if this modification was really needed. Did it really make a difference if one used a quadratic loss or a hinge loss? And in much of his subsequent beautiful work on manifold learning he consistently compared the two, and I suspect his skepticism was justified. Partha also questioned the dominant HMM paradigm in speech recognition, he questioned whether we really need language level models to disambiguate the acoustic signal, or have we all simply been using the wrong processing of this signal. Partha's thinking on problems in AI was always motivated by observations on human perception. He would often dwell on how much background noise and clutter there is in a typical environment in which we listen to speech, and how sensitive existing speech recognition algorithms are to such noise. He would emphasize how adaptable and invariant human recognition is compared to machine algorithms. More than once he told me that he himself had never talked on the phone before his teenage years. That in no way affected his ability to understand speech on the phone once he did pick up the receiver. These conversations eventually led us to a joint project aimed at developing a more robust speech recognition algorithm. And true to his nature, Partha always questioned whether we had really achieved any progress?

So when the double rap came I knew I was in for some tough questions, and, beyond that, a very long conversation covering a myriad of topics. Because, you see, the question of robustness of human perception, the question of how much high level knowledge is required to understand speech, is closely connected to the questions Chomsky asked with respect to language. And as someone who had studied language and linguistics, and had done his Ph.D. at MIT, Partha took Chomsky's theories very seriously. We spent quite a few meetings with Partha introducing me to Chomsky's theory of a universal grammar. And after the first conversation touching on Chomsky we discovered that we both shared a great deal of respect for him as a political and social thinker. So you can imagine a conversation that started with a pointed question on say mixture models for the speech signal, and evolved into a higher level conversation on robust speech recognition, could very well end up with a discussion on Chomsky's positions on the Middle East conflict or US foreign policy. Now keep in mind that whereas Partha was more of an afternoon person, I am an early morning person, and that double rap at 3PM meant that I may not get home until quite late. But I really couldn't resist. I couldn't resist the richness and breadth of the conversations Partha triggered and engaged me in. He was a real renaissance person, both in his scientific interests, contributing in his research to a very broad range of topics, all somehow connected to artificial or human intelligence. and beyond that in his cultural and social interests, from classical Indian music, to Indian history, to economic theory, and on and on. Partha's passing is a great loss for his family, for his friends, for his colleagues, for his students, for the Computer Science and Statistics Departments, and for the University as a whole. But his inquisitive spirit will stay on with us, the questions he asked will continue to intrigue us, and the methods he developed will surely help us in our attempts to find some answers.

If you would like to contribute to this page, please send an email to John Goldsmith (