Learning from Experience

Stephanie Rosenthal, Reid Simmons

Carnegie Mellon University, Learning and Explaining the Differences Between Novice and Expert Data Analysts

Tom M. Mitchell, Brad Myers

Carnegie Mellon University, Machine Learning from Human Instruction: Every Person a Programmer

Agostino Capponi

Columbia University, Robo-Advising as a Symbiotic Human- Machine System

Yolanda Gil, Deborah Khider

University of Southern California, Automated Machine Learning for Time Series Analysis

Ion Stoica

University of California, Berkeley, A Unified Library for Distributed Reinforcement Learning

Shimon Whiteson

University of Oxford, Cooperative Multi-Agent Reinforcement Learning

Anisoara Calinescu, Doyne Farmer, Michael Wooldridge

University of Oxford, Risk Management of Investment Strategies: An Agent-based Approach

Sarit Kraus

Bar-Ilan University, Israel, Agents supporting large-scale environments of teams of people and computer systems

Sergey Levine

University of California, Berkeley, Scalable Language-Guided Deep Reinforcement Learning

Explainability & Interpretability

Ofra Amir, David Sarne, Finale Doshi-Velez

Bar-Ilan University, Israel, Summarizing Agent Behavior to People

Adnan Darwiche

University of California, Los Angeles, Explaining Decisions of Machine Learning Systems

Suman Jana, Jeannette M. Wing, Junfeng Yang

Columbia University, Efficient Formal Safety Analysis of Neural Networks

Xiang Ren

University of Southern California, Interpretable Knowledge Reasoning and Extraction for Equity Investment

Daniela Rus

Massachusetts Institute of Technology, Compression Algorithms for Resilient AI

Ning Chen, Hang Su, Jun Zhu

Tsinghua University, Interpretable machine learning by incorporating human knowledge; Adversarial attack and defense on image classification; Adversarial attacks and defense on graph data

Ameet Talwalkar

Carnegie Mellon University, Illuminating Black-Box Models in Machine Learning

Ryan P. Adams

Princeton University, “Optimizer, explain thyself!”: Making Bayesian Optimization Interpretable

Subbarao Kambhampati

Arizona State University, Human-Aware AI Assistants for Interactive Decision Support in Finance

Xia “Ben” Hu

Texas A&M University, Post-hoc Prediction Interpretation of Deep Learning in Finance Applications

Daniel Hsu

Columbia University, Prediction semantics and interpretations that are grounded in real data

Xu Chu

Georgia Institute of Technology, Contextual Model Interpretation

Data & Cryptography

Erik Demaine

Massachusetts Institute of Technology, Energy-Efficient Algorithms for AI and Data Science

Rafail Ostrovsky

University of California Los Angeles, SIENA: Securing AI Computing Environment for AWS

John Lafferty

Massachusetts Institute of Technology, Energy-Efficient Algorithms for AI and Data Science

Kay Giesecke

Stanford University, Exploring Use Cases for JP Morgan ROAR in Academic Teaching and Research

Avigdor Gal

Technion Israel Institute of Technology, Teaching the Machine to Solve Matching Problems

Vipul Goyal

Carnegie Mellon University, Secure Multi-Party Computation for Privacy Preserving Data Mining

Ethics & Fairness

Ariel D. Procaccia

Carnegie Mellon University, Voting-Based Methods for Explainable AI

Zhiwei Steven Wu

University of Minnesota, Preventing Unfair Discrimination in Interactive Learning

Nathan Kallus

Cornell University, Robustness and Fairness in Policy Learning from Observational Data


Joydeep Biswas

University of Massachusetts Amherst, A Scalable Approach to Correcting Failures of AI Systems in the Real World

Furong Huang, Louiqa Raschid, Alberto Rossi

University of Maryland, Methods to Identify Communities and Trading Behavior Over Financial Data Streams

Nikolas Kantas, Panos Parpas, Grigorios A. Pavliotis

Imperial College London, Dynamics, Control and Uncertainty Quantification for Stable Machine Learning Algorithms