I am an Assistant Professor in the Technology and Operations Management Group at Harvard Business School. My research primarily involves machine learning and its applications to high-stakes decision making.
I am an Assistant Professor in the Technology and Operations Management Group at Harvard Business School. My research primarily involves machine learning and its applications to high-stakes decision making.
As predictive models increasingly assist human experts (e.g., doctors) in day-to-day decision making, it is crucial for experts to be able to explore and understand how such models behave in different feature subspaces in order to know if and when to trust them. To this end, we propose Model Understanding through Subspace Explanations (MUSE), a novel model agnostic framework which facilitates understanding of a given black box model by explaining how it behaves in subspaces characterized by certain features of interest. Our framework provides end users (e.g., doctors) with the flexibility of customizing the model explanations by allowing them to input the features of interest. The construction of explanations is guided by a novel objective function that we propose to simultaneously optimize for fidelity to the original model, unambiguity and interpretability of the explanation. More specifically, our objective allows us to learn, with optimality guarantees, a small number of compact decision sets each of which captures the behavior of a given black box model in unambiguous, well-defined regions of the feature space. Experimental evaluation with real-world datasets and user studies demonstrate that our approach can generate customizable, highly compact, easy-to-understand, yet accurate explanations of various kinds of predictive models compared to state-of-the-art baselines.
Lakkaraju, Himabindu, Ece Kamar, Rich Caruana, and Jure Leskovec. "Interpretable and Explorable Approximations of Black Box Models." Paper presented at the 4th Workshop on Fairness, Accountability, and Transparency in Machine Learning, Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD), Halifax, NS, Canada, August 14, 2017.
View Details
Lakkaraju, Himabindu, Ece Kamar, Rich Caruana, and Eric Horvitz. "Discovering Unknown Unknowns of Predictive Models." Paper presented at the 30th Annual Conference on Neural Information Processing Systems (NIPS), Workshop on Reliable Machine Learning in the Wild, Barcelona, Spain, December 9, 2016.
View Details
Himabindu Lakkaraju, Jon Kleinberg, Jure Leskovec, Jens Ludwig and Sendhil Mullainathan
Citation:
Lakkaraju, Himabindu, Jon Kleinberg, Jure Leskovec, Jens Ludwig, and Sendhil Mullainathan. "Using Big Data to Improve Social Policy." NBER Economics of Crime Working Group, 2014.
View Details
Lakkaraju, Himabindu, Richard Socher, and Chris Manning. "Aspect Specific Sentiment Analysis Using Hierarchical Deep Learning." Paper presented at the 28th Annual Conference on Neural Information Processing Systems (NIPS), Workshop on Deep Learning and Representation Learning, Montreal, Canada, December 12, 2014.
View Details
Lakkaraju, Himabindu, and Hyung-Il Ahn. "A Non Parametric Theme Event Topic Model for Characterizing Microblogs." Paper presented at the 25th Annual Conference on Neural Information Processing Systems (NIPS), Workshop on Computational Science and the Wisdom of Crowds, Granada, Spain, December 17, 2011.
View Details
Lakkaraju, Himabindu, and Angshu Rai. "Unified Modeling of User Activities on Social Networking Sites." Paper presented at the 25th Annual Conference on Neural Information Processing Systems (NIPS), Workshop on Computational Science and the Wisdom of Crowds, Granada, Spain, December 17, 2011.
View Details
