University of Massachusetts Amherst

Search Google Appliance

Links

Yexiang Xue - Combining Reasoning and Learning for Data Science and Decision Making: Integrating Concepts from AI, Sustainability, and Scientific Discovery

DS Seminar
April 18, 4:00pm
Computer Science Building, Room 150/151


 

Yexiang Xue
Cornell University

Title:  Combining Reasoning and Learning for Data Science and Decision Making: Integrating Concepts from AI, Sustainability, and Scientific Discovery

Abstract:  Problems at the intersection of reasoning, optimization, and learning often involve multi-stage inference and are therefore highly intractable. He will introduce a novel computational framework, based on embeddings, to tackle multi-stage inference problems. As a first example, he will present a novel way to encode the reward allocation problem for a two-stage organizer-agent game-theoretic framework as a single stage optimization problem. The encoding embeds an approximation of the agents’ decision-making process into the organizer’s problem. We apply this methodology to eBird, a well-established citizen-science program for collecting bird observations, as a game called Avicaching. Our AI-based reward allocation was shown highly effective, surpassing the expectations of the eBird organizers and bird conservation experts. As a second example, he will present a novel constant approximation algorithm to solve the so-called Marginal Maximum-A-Posteriori (MMAP) problem for finding the optimal policy maximizing the expectation of a stochastic objective. To tackle this problem, he will propose the embedding of its intractable counting subproblems as queries to NP-oracles subject to additional XOR constraints. As a result, the entire problem is encoded as a single NP-equivalent optimization. The approach outperforms state-of-the-art solvers based on variational inference as well as MCMC sampling on probabilistic inference benchmarks, deep learning applications, as well as on a novel decision-making application in network design for wildlife conservation. Lastly, he will talk about how a novel integration of reasoning and learning has led to the discovery of new solar light absorbers by solving a dimensionality reduction problem to characterize the crystal structures of metal oxide materials using X-ray diffraction data.    


A reception will be held at 3:40 P.M. in the atrium outside the presentation room.