Northwestern Computer Science had a strong presence at the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), held December 10-16 in New Orleans.
See Also
Announcing the NeurIPS 2023 Paper Awards – NeurIPS BlogNeurIPS Highlights | ML Contests10 Highlights from NeurIPS 2023AIhub monthly digest: December 2023 – attending NeurIPS, generating 3d models of blood vessels, and the Wizard of AI - ΑΙhubNeurIPS is the premier annual forum for interdisciplinary research in fields including machine learning, computational neuroscience, reinforcement learning, computer vision, natural language processing, statistics, and optimization.
See Also
RegistrationNorthwestern Engineering’s Han Liu, Konstantin Makarychev, V.S. Subrahmanian, Xiao Wang, Zhaoran Wang, Ying Wu, and Xinyu Xing and several of their current and former PhD students and postdocs presented impactful research at the event.
“NeurIPS is one of the most prestigious and highly ranked conferences in machine learning, artificial intelligence, and data science,” said Makarychev, a professor of computer science at the McCormick School of Engineering. “This year, we had a number of very strong publications at this conference.”
Northwestern contributions to the NeurIPS 2023 technical program included:
- “On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis” — Sayak Chakrabarty, PhD student in theoretical computer science at Northwestern Engineering, and Arghya Datta (University of Montreal)
- “On Sparse Modern Hopfield Model” — Han Liu, Orrington Lunt Professor of Computer Science at Northwestern Engineering and professor of statistics at Northwestern’s Weinberg College of Arts and Sciences; Jerry Yao-Chieh Hu, PhD student in computer science advised by Liu; master’s degree students in computer science Dennis Wu and Chenwei Xu; Donglin Yang, a former PhD student of computer science at Northwestern Engineering who is completing a doctoral program at the University of British Columbia; and Bo-Yu Chen (National Taiwan University)
- “Single-Pass Pivot Algorithm for Correlation Clustering. Keep it simple!” — Makarychev and Chakrabarty
- “Random Cuts are Optimal for Explainable k-Medians” — Makarychev and Liren Shan, a PhD candidate in computer science advised by Makarychev and a research assistant professor at the Toyota Technological Institute at Chicago
- “Computing Optimal Nash Equilibria in Multiplayer Games” – V.S. Subrahmanian, Walter P. Murphy Professor of Computer Science in Northwestern Engineering and a faculty fellow at Northwestern Roberta Buffett Institute for Global Affairs; Youzhi Zhang, a former postdoctoral researcher mentored by Subrahmanian who is currently an assistant professor at the Hong Kong Institute of Science and Innovation; and Bo An (Nanyang Tech University, Singapore)
- “Constant Approximation for Individual Preference Stable Clustering” — Pattara Sukprasert (PhD ’23), a software engineer at Databricks who was advised by Samir Khuller, Peter and Adrienne Barris Chair of Computer Science; Anders Aamand, Justin Y. Chen, Allen Liu, and Sandeep Silwal (MIT); Ali Vakilian (Toyota Technological Institute at Chicago); and Fred Zhang (University of California, Berkeley)
- “Robust and Actively Secure Serverless Collaborative Learning” —Xiao Wang, assistant professor of computer science; Olive Franzese, PhD student in computer science; Christopher A. Choquette-Choo (Google), Adam Dziedzic (CISPA Helmholtz Center for Information Security), Congyu Fang, Muhammad Ahmad Kaleem, Nicolas Papernot, Stephan Rabanser, and Mark R. Thomas (University of Toronto and Vector Institute), Somesh Jha (Google and University of Wisconsin-Madison)
- “TOA: Task-oriented Active VQA” — Ying Wu, professor of electrical and computer engineering and (by courtesy) computer science at Northwestern Engineering, Mingfu Liang and Xiaoying Xing, both PhD students in electrical and computer engineering
- “Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms” — Zhaoran Wang, assistant professor of industrial engineering and management sciences and (by courtesy) computer science; Boyi Liu and Shenao Zhang, PhD students in industrial engineering; and Tuo Zhao (Georgia Institute of Technology)
- “Learning Regularized Monotone Graphon Mean-Field Games” — Zhaoran Wang, Vincent Tan and Fengzhuo Zhang (National University of Singapore), and Zhuoran Yang (Yale University)
- “Posterior Sampling for Competitive RL: Function Approximation and Partial Observation” — Zhaoran Wang, Ziyu Dai (New York University), Shuang Qiu and Tong Zhang (Hong Kong University of Science and Technology), Zhuoran Yang (Yale University), and Han Zhong (Peking University)
- “One Objective to Rule Them All: A Maximization Objective Fusing Estimation and Planning for Exploration” — Zhaoran Wang, IEMS PhD students Zhihan Liu, Shenao Zhang, and Sirui Zheng, Miao Lu (Stanford University), Wei Xiong (University of Illinois Urbana-Champaign), Han Zhong (Peking University), Hao Hu (Tsinghua University), and Zhuoran Yang (Yale University)
- “StateMask: Explaining Deep Reinforcement Learning through State Mask” — associate professor of computer science Xinyu Xing; PhD students in computer science Zelei Cheng, Xian Wu, Jiahao Yu; and Wenbo Guo and Wenhai Sun (Purdue University)
