NIPS Logo
NeurIPS, the top AI and ML conference, is being held in New Orleans from December 10 to December 16. Princeton students, postdocs, and faculty will be there presenting a wide array of work. This post summarizes Princeton research being presented at the conference, highlighting the breadth of machine learning work happening here. At Princeton, AI/ML research happens not just in computer science, but also in a range of other departments (e.g., electrical engineering, mechanical engineering, physics) and institutes/centers (e.g., neuroscience, PLI, CSML). Departmental boundaries do not impede collaborations, but rather speak to the breadth of AI/ML applications and expertise.
Join us! Princeton is looking for PhD students (deadline Dec 15) and postdocs (PLI rolling deadline starting Dec 1; CSML deadline Dec 15), research software engineers (rolling deadline), and research scientists (rolling deadline). If you'll be at NeurIPS, come say "hi"!
Main Conference Proceedings
(Oral) When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Authors: Tianwei Ni, Michel Ma, Benjamin Eysenbach, Pierre-Luc Bacon
Links: Paper
(Oral) Fine-Tuning Language Models with Just Forward Passes
Authors: Sadhika Malladi*, Tianyu Gao*, Eshaan Nichani, Alex Damian, Jason Lee, Danqi Chen, Sanjeev Arora
Links: Paper
(Oral) Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
Authors: Alex Damian, Eshaan Nichani, Rong Ge, Jason Lee
Links: Paper
(Oral) Learning Transformer Programs
Authors: Dan Friedman, Alexander Wettig, Danqi Chen
Links: Paper
(Oral) Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Authors: Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, Karthik Narasimhan
Links: Paper
(Oral) Siamese Masked Autoencoders
Authors: Agrim Gupta, Jiajun Wu, Jia Deng, Fei-Fei Li
Links: Paper
(Spotlight) Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors
Authors: Paul Steven Scotti, Atmadeep Banerjee, Jimmie Goode, Stepan Shabalin, Alex Nguyen, Cohen Ethan, Aidan James Dempster, Nathalie Verlinde, Elad Yundler, David Weisberg, Kenneth Norman, Tanishq Mathew Abraham
Links: Paper
(Spotlight) Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
Authors: Eshaan Nichani, Alex Damian, Jason D. Lee
Links: Paper
(Spotlight) Differentially Private Image Classification by Learning Priors from Random Processes
Authors: Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal
Links: Paper
(Spotlight) Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker
Authors: Sihui Dai, Wenxin Ding, Arjun Nitin Bhagoji, Daniel Cullina, Heather Zheng, Ben Zhao, Prateek Mittal
Links: Paper
(Spotlight) A Privacy-Friendly Approach to Data Valuation
Authors: Jiachen (Tianhao) Wang, Yuqing Zhu, Yu-Xiang Wang, Ruoxi Jia, Prateek Mittal
Links: Paper
(Spotlight) Alignment with human representations supports robust few-shot learning
Authors: Ilia Sucholutsky, Tom Griffiths
Links: Paper
(Spotlight) Online Control for Meta-optimization
Authors: Xinyi Chen, Elad Hazan
Links: Paper
Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models
Authors: Naoki Egami, Musashi Hinck, Brandon M. Stewart, Hanying Wei
Links: Paper
HIQL: Offline Goal-Conditioned RL with Latent States as Actions
Authors: Seohong Park, Dibya Ghosh, Benjamin Eysenbach, Sergey Levine
Links: Paper
Is RLHF More Difficult than Standard RL?
Authors: Yuanhao Wang, Qinghua Liu, Chi Jin
Links: Paper
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
Authors: Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
Links: Paper
Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning
Authors: Gen Li*, Wenhao Zhan*, Jason D Lee, Yuejie Chi, Yuxin Chen
Links: Paper
DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Authors: Ahmed Khaled, Konstantin Mishchenko, Chi Jin
Links: Paper
Kissing to Find a Match: Efficient Low-Rank Permutation Representation
Authors: Hannah Dröge, Zorah Lähner, Yuval Bahat, Onofre Martorell, Felix Heide, Michael Möller
Links: Paper
Boundary Guided Learning-Free Semantic Control with Diffusion Models
Authors:Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan
Links: Paper
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability
Authors: Jingfeng Wu, Vladimir Braverman, Jason Lee
Links: Paper
Online Nonstochastic Model-Free Reinforcement Learning
Authors: Udaya Ghai, Arushi Gupta, Wenhan Xia, Karan Singh, Elad Hazan
Links: Paper
Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models
Authors: Deepak Narayanan, Keshav Santhanam, Peter Henderson, Rishi Bommasani, Tony Lee, Percy Liang
Links: Paper
Im-Promptu: In-Context Composition from Image Prompts
Authors: Bhishma Dedhia, Michael Chang, Jake Snell, Tom Griffiths, Niraj Jha
Links: Paper
Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning
Authors: Yifan Zang, Jinmin He, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng
Links: Paper
Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Authors: Zi Wang, Alexander Ku, Jason Baldridge, Tom Griffiths, Been Kim
Links: Paper
Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping
Authors: Chunming He, Kai Li, Yachao Zhang, Guoxia Xu, Longxiang Tang, Yulun Zhang, Zhenhua Guo, Xiu Li
Links: Paper
Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Authors: Vladimir Feinberg, Xinyi Chen, Y. Jennifer Sun, Rohan Anil, Elad Hazan
Links: Paper
Context-lumpable stochastic bandits
Authors: Chung-Wei Lee, Qinghua Liu, Yasin Abbasi Yadkori, Chi Jin, Tor Lattimore, Csaba Szepesvari
Links: Paper
Optimal Rates for Bandit Nonstochastic Control
Authors: Y. Jennifer Sun, Stephen Newman, Elad Hazan
Links: Paper
Deep Patch Visual Odometry
Authors: Zachary Teed, Lahav Lipson, Jia Deng
Links: Paper
Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
Authors: Hui Yuan, Kaixuan Huang, Chengzhuo Ni, Minshuo Chen, Mengdi Wang
Links: Paper
Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Authors: Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yian Ma
Links: Paper
A Randomized Approach to Tight Privacy Accounting
Authors: Jiachen (Tianhao) Wang, Saeed Mahloujifar, Tong Wu, Ruoxi Jia, Prateek Mittal
Links: Paper
PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction
Authors: Apoorva Sharma, Sushant Veer, Asher Hancock, Heng Yang, Marco Pavone, Anirudha Majumdar
Links: Paper
Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
Authors: Minshuo Chen, Yu Bai, H. Vincent Poor, Mengdi Wang
Links: Paper
Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
Authors: Zeyu Zhang, Yi Su, Hui Yuan, Yiran Wu, Rishab Balasubramanian, Qingyun Wu, Huazheng Wang, Mengdi Wang
Links: Paper
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
Authors: Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason Lee
Links: Paper
Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage
Authors: Masatoshi Uehara, Nathan Kallus, Jason Lee, Wen Sun
Links: Paper
Partial Matrix Completion
Authors: Elad Hazan, Adam Tauman Kalai, Varun Kanade, Clara Mohri, Y. Jennifer Sun
Links: Paper
InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
Authors: John Yang, Akshara Prabhakar, Karthik Narasimhan, Shunyu Yao
Links: Paper
Reflexion: language agents with verbal reinforcement learning
Authors: Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao
Links: Paper
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
Authors: Vikram V. Ramaswamy, Sing Yu Lin, Dora Zhao, Aaron Adcock, Laurens van der Maaten, Deepti Ghadiyaram, Olga Russakovsky
Links: Paper
Workshops
Mathematics of Modern Machine Learning (M3L)
Feature Learning in Infinite-Depth Neural Networks
Authors: Greg Yang*, Dingli Yu*, Chen Zhu, Soufiane Hayou
Links: Paper
Workshop on robustness of zero/few-shot learning in foundation models (R0-FoMo)
Trainable Transformer in Transformer
Authors: Abhishek Panigrahi, Sadhika Malladi, Mengzhou Xia, Sanjeev Arora
Links: Paper
InstructEval: Systematic Evaluation of Instruction Selection Methods
Authors: Anirudh Ajith*, Chris Pan*, Mengzhou Xia, Ameet Deshpande, Karthik Narasimhan
Links: Paper
Workshop on Distribution Shifts: New Frontiers with Foundation Models
Do Transformers Parse while Predicting the Masked Word?
Authors: Haoyu Zhao*, Abhishek Panigrahi*, Rong Ge, Sanjeev Arora
Links: Paper
Skill-Mix: A Flexible and Expandable Family of Evaluations for AI Models
Authors: Dingli Yu, Simran Kaur, Arushi Gupta, Jonah Brown-Cohen, Anirudh Goyal, Sanjeev Arora
Links: Paper
Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
Authors: Jiawei Ge, Shange Tang, Jianqing Fan, Cong Ma, Chi Jin
Links: Paper
Goal Conditioned Reinforcement Learning
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
Authors: Chongyi Zheng, Benjamin Eysenbach, Homer Walke, Patrick Yin, Kuan Fang, Ruslan Salakhutdinov, Sergey Levine
Links: Paper
Contrastive Difference Predictive Coding
Authors: Chongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach
Links: Paper
Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View.
Authors: Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
Links: Paper
Generalization in Planning (GenPlan '23)
Contrastive Representations Make Planning Easy
Authors: Benjamin Eysenbach, Vivek Myers, Sergey Levine, Ruslan Salakhutdinov
Links: Paper
Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Authors: Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, Danqi Chen
Links: Paper
Third Workshop on Efficient Natural Language and Speech Processing (ENLSP-III): Towards the Future of Large Language Models and their Emerging Descendants
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Authors: Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, Danqi Chen
Links: Paper
MATH-AI: The 3rd Workshop on Mathematical Reasoning and AI
Llemma: An Open Language Model For Mathematics
Authors: Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen McAleer, Albert Jiang, Jia Deng, Stella Biderman, Sean Welleck
Links: Paper
(Contributed Talk) OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
Authors: Keiran Paster, Marco Dos Santos, Zhangir Azerbayev, Jimmy Ba
Links: Paper
Regulatable ML @NeurIPS2023
Detecting Pretraining Data from Large Language Models
Authors: Weijia Shi*, Anirudh Ajith*, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, Luke Zettlemoyer
Links: Paper
AI for Scientific Discovery: From Theory to Practice
Representation Learning for Spatial Multimodal Data Integration with Optimal Transport
Authors: Xinhao Liu, Benjamin Raphael
Links: Paper