Artificial Agents Use Reinforcement Learning to Explain Actions, a Necessary Step as They Get Smarter

By Nathan Deen

Oral

Deep Generalized Schrödinger Bridge
Guan-Horng Liu (Georgia Institute of Technology); Tianrong Chen (Georgia Institute of Technology); Oswin So (Massachusetts Institute of Technology); Evangelos Theodorou (Georgia Institute of Technology)

End-to-end Stochastic Optimization with Energy-based Model
Lingkai Kong (Georgia Institute of Technology); Jiaming Cui (Georgia Institute of Technology); Yuchen Zhuang (Georgia Institute of Technology); Rui Feng (Georgia Institute of Technology); B. Aditya Prakash (Georgia Institute of Technology); Chao Zhang (Georgia Institute of Technology)

Uncovering the Structural Fairness in Graph Contrastive Learning
Ruijia Wang (Beijing University of Posts and Telecommunications); Xiao Wang (Beijing University of Posts and Telecommunications); Chuan Shi (Beijing University of Post and Telecommunication, Tsinghua University); Le Song (College of Computing, Georgia Institute of Technology)

Poster

Adapting Self-Supervised Vision Transformers by Probing Attention-Conditioned Masking Consistency
Viraj Uday Prabhu (Georgia Institute of Technology); Sriram Yenamandra (Georgia Institute of Technology); Aaditya Singh (Georgia Institute of Technology); Judy Hoffman (Georgia Institute of Technology)

Adaptive Oracle-Efficient Online Learning
Guanghui Wang (Georgia Institute of Technology); Zihao Hu (Georgia Institute of Technology); Vidya Muthukumar (Georgia Institute of Technology); Jacob Abernethy (Georgia Tech Research Corporation)

Alternating Mirror Descent for Constrained Min-Max Games
Andre Wibisono (Yale University); Molei Tao (Georgia Institute of Technology); Georgios Piliouras (Singapore University of Technology and Design)

Bayesian Risk Markov Decision Processes
Yifan Lin (Georgia Institute of Technology); Yuxuan Ren (Georgia Institute of Technology); Enlu Zhou (Georgia Tech Research Corporation)

Causal Discovery in Linear Latent Variable Models Subject to Measurement Error
Yuqin Yang (Georgia Institute of Technology); AmirEmad Ghassami (Johns Hopkins University); Mohamed S Nafea (University of Detroit Mercy); Negar Kiyavash (Swiss Federal Institute of Technology Lausanne); Kun Zhang (Carnegie Mellon University); Ilya Shpitser (Johns Hopkins University)

Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning
Shenao Zhang (Georgia Institute of Technology)

Distinguishing discrete and continuous behavioral variability using warped autoregressive HMMs
Julia C Costacurta (Stanford University); Lea Duncker (Stanford University); Blue Sheffer (Stanford University); Winthrop Gillis (Harvard University, Harvard University); Caleb Weinreb (Harvard University); Jeffrey Markowitz (Georgia Institute of Technology); Sandeep R. Datta (Harvard University); Alex H Williams (New York University); Scott Linderman (Stanford University)

Distributionally robust weighted k-nearest neighbors
Shixiang Zhu (Carnegie Mellon University); Liyan Xie (The Chinese University of Hong Kong, Shenzhen); Minghe Zhang (Georgia Institute of Technology); Rui Gao (University of Texas, Austin); Yao Xie (Georgia Institute of Technology)

Inherently Explainable Reinforcement Learning in Natural Language
XIANGYU PENG (Georgia Institute of Technology); Mark Riedl (Georgia Institute of Technology); Prithviraj Ammanabrolu (Allen Institute for Artificial Intelligence)

Introspective Learning : A Two-Stage approach for Inference in Neural Networks
Mohit Prabhushankar (Georgia Institute of Technology); Ghassan AlRegib (Georgia Institute of Technology)

Kernel Multimodal Continuous Attention
Alexander Moreno (Luminous Computing); Zhenke Wu (University of Michigan, Ann Arbor); Supriya Nagesh (Georgia Institute of Technology); Walter H. Dempsey (University of Chicago); James Matthew Rehg (Georgia Institute of Technology)

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
Stefan Stojanov (Georgia Institute of Technology); Ngoc Anh Thai (Georgia Institute of Technology); Zixuan Huang (Georgia Institute of Technology); James Matthew Rehg (Georgia Institute of Technology)

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
Yonggan Fu (Rice University and Georgia Tech); Yang Zhang (International Business Machines); Kaizhi Qian (International Business Machines); Zhifan Ye (Rice University); Zhongzhi Yu (Rice University and Georgia Tech); Cheng-I Lai (Massachusetts Institute of Technology); Yingyan Lin (Rice University and Georgia Tech)

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
hanxue liang (Swiss Federal Institute of Technology); Zhiwen Fan (University of Texas, Austin); Rishov Sarkar (Georgia Institute of Technology); Ziyu Jiang (Texas A&M); Tianlong Chen (University of Texas, Austin); Kai Zou (Protagolabs Inc); Yu Cheng (Microsoft Research); Cong Hao (Georgia Institute of Technology); Zhangyang Wang (University of Texas, Austin)

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds
Biraj Dahal (Georgia Institute of Technology); Alexander Havrilla (Georgia Institute of Technology); Minshuo Chen (Princeton University); Tuo Zhao (Georgia Institute of Technology); Wenjing Liao (Georgia Institute of Technology)

Optimal Scaling for Locally Balanced Proposals in Discrete Spaces
Haoran Sun (Georgia Institute of Technology); Hanjun Dai (Google Research); Dale Schuurmans (University of Alberta)

PAC Prediction Sets for Meta-Learning
Sangdon Park (Georgia Institute of Technology); Edgar Dobriban (The Wharton School, University of Pennsylvania); Insup Lee (University of Pennsylvania); Osbert Bastani (University of Pennsylvania)

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks
Yen-Cheng Liu (Georgia Institute of Technology); Chih-Yao Ma (Facebook); Junjiao Tian (Georgia Institute of Technology); Zijian He (Meta); Zsolt Kira (Georgia Institute of Technology)

Polynomial time guarantees for the Burer-Monteiro method
Diego Cifuentes (Georgia Institute of Technology); Ankur Moitra (Massachusetts Institute of Technology)

Recruitment Strategies That Take a Chance
Gregory Kehne (Harvard University); Ariel D. Procaccia (Harvard University); Jingyan Wang (Georgia Institute of Technology)

Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games
Sihan Zeng (Georgia Institute of Technology); Thinh T. Doan (Virginia Polytechnic Institute and State University); Justin Romberg (Georgia Institute of Technology)

Reinforced Genetic Algorithm for Structure-based Drug Design
Tianfan Fu (Georgia Institute of Technology); Wenhao Gao (Massachusetts Institute of Technology); Connor W. Coley (Massachusetts Institute of Technology); Jimeng Sun (University of Illinois, Urbana Champaign)

Robust Bayesian Regression via Hard Thresholding
Fan Zheyi (Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Chinese Academy of Sciences); Zhaohui Li (Georgia Institute of Technology); Qingpei Hu (University of the Chinese Academy of Sciences)

Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space
Yunbum Kook (Georgia Institute of Technology); YinTat Lee (University of Washington, Seattle); Ruoqi Shen (University of Washington, Seattle); Santosh Vempala (Georgia Institute of Technology)

Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers
Ran Liu (Georgia Institute of Technology); Mehdi Azabou (Georgia Institute of Technology); Max Dabagia (Georgia Institute of Technology); Jingyun Xiao (Georgia Institute of Technology); Eva L Dyer (Georgia Institute of Technology)

Subquadratic Kronecker Regression with Applications to Tensor Decomposition
Matthew Fahrbach (Google); Gang Fu (Google Research); Mehrdad Ghadiri (Georgia Institute of Technology)

Surprising Instabilities in Training Deep Networks and a Theoretical Analysis
Yuxin Sun (Georgia Institute of Technology); Dong Lao (University of California, Los Angeles); Ganesh Sundaramoorthi (KAUST); Anthony Yezzi (Georgia Tech)

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
Yanbo Xu (Georgia Institute of Technology); Alind Khare (Georgia Institute of Technology); Glenn Matlin (Georgia Institute of Technology); Monish Ramadoss (Georgia Institute of Technology); Rishikesan Kamaleswaran (Emory University); Chao Zhang (Georgia Institute of Technology); Alexey Tumanov (Georgia Institute of Technology)

Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation
Haoyu Peter Wang (Purdue University); Nan Wu (UC Santa Barbara); Hang Yang (Nankai University); Cong Hao (Georgia Institute of Technology); Pan Li (Purdue University)

VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement
Erik Wijmans (Georgia Institute of Technology); Irfan Essa (Georgia Institute of Technology); Dhruv Batra (Georgia Institute of Technology)

ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings
Arjun Majumdar (Georgia Institute of Technology); Gunjan Aggarwal (Georgia Institute of Technology); Bhavika Suresh Devnani (Georgia Institute of Technology); Judy Hoffman (Georgia Institute of Technology); Dhruv Batra (Georgia Institute of Technology)

Datasets and Benchmarks

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
Nolan Wagener, Andrey Kolobov, Felipe Vieira Frujeri, Ricky Loynd, Ching-An Cheng, Matthew Hausknecht

MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction
Jorge Quesada, Lakshmi Sathidevi, Ran Liu, Nauman Ahad, Joy M Jackson, Mehdi Azabou, Jingyun Xiao, Chris Liding, Matthew Jin, Carolina Urzay, William Gray-Roncal, Erik Christopher Johnson, Eva L Dyer

OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
Mohit Prabhushankar1, Kiran Kokilepersaud1, Yash-yee Logan1, Stephanie Trejo Corona, Ghassan AlRegib, Charles Wykoff

PulseImpute: A Novel Benchmark Task for Pulsative Physiological Signal Imputation
Maxwell Xu, Alexander Moreno, Supriya Nagesh, Varol Burak Aydemir, David W Wetter, Santosh Kumar, James Matthew Rehg

Workshops

Accelerated Federated Optimization with Quantization
Yeojoon Youn, Bhuvesh Kumar, Jacob Abernethy

Active metric learning and classification using similarity queries
Namrata Nadagouda, Austin Xu, Mark A. Davenport

AsymQ: Asymmetric Q-loss to mitigate overestimation bias in off-policy reinforcement learning
Anonymous

Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation
Viraj Uday Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

Clinical Contrastive Learning for Biomarker Detection
Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib

Data-driven discovery of non-Newtonian astronomy via learning non-Euclidean Hamiltonian
Oswin So, Gongjie Li, Evangelos A. Theodorou, Molei Tao

End-to-End Multimodal Representation Learning for Video Dialog
Huda Alamri, Anthony Bilic, Michael Hu, Apoorva Beedu, Irfan Essa

Fast Sampling of Diffusion Models with Exponential Integrator
Qinsheng Zhang, Yongxin Chen

Generating Synthetic Datasets by Interpolating along Generalized Geodesics
Jiaojiao Fan, David Alvarez-Melis

HandsOff: Labeled Dataset Generation with No Additional Human Annotations
Anonymous

Imperceptible Adversarial Attacks on Discrete-Time Dynamic Graph Models
Kartik Sharma, Rakshit Trivedi, Rohit Sridhar, Srijan Kumar

Improving Assistive Robotics with Deep Reinforcement Learning
Yash Jakhotiya, Iman Haque

Incorporating Higher Order Constraints for Training Surrogate Models to Solve Inverse Problems
Jihui Jin, Nick Durofchalk, Richard Touret, Karim Sabra, Justin Romberg

Keynote talk at NeurIPS 2022 Temporal Graph Learning Workshop
Srijan Kumar

Loop Unrolled Shallow Equilibrium Regularizer (LUSER) – A Memory-Efficient Inverse Problem Solver
Peimeng Guan, Jihui Jin, Justin Romberg, Mark A. Davenport

On the Ramifications of Human Label Uncertainty
C. Zhou, M. Prabhushankar, and G. AlRegib

Performance and utility trade-off in interpretable sleep staging
Irfan Al-Hussaini, Cassie S. Mitchell

Social Construction of XAI: Do We Need One Definition to Rule Them All?
Upol Ehsan, Mark O. Riedl

Video based Object 6D Pose Estimation using Transformers
Apoorva Beedu, Huda Alamri, Irfan Essa

Tutorial

Creative Culture and Machine Learning
Negar Rostamzadeh, Cheng-Zhi Anna Huang, Mark Riedl