Deep Learning

Much of our work leverages advances in representation learning. However, although deep learning plays an important role in most of our work, it's often not the central role. Rather than tweaking architectures, we're more interested in how deep learning alters the landscape of more fundamental problems of interest.

• Downstream Datasets Make Surprisingly Good Pretraining Corpora

  Kundan Krishna, Saurabh Garg, Jeffrey Bigham, Zachary Lipton
  ACL 2023

• Disentangling the Mechanisms Behind Implicit Regularization in SGD

  Zachary Novack, Simran Kaur, Tanya Marwah, Saurabh Garg, Zachary Lipton
  International Conference on Learning Representations (ICLR)

• Deconstructing distributions: A pointwise framework of learning

  Gal Kaplun, Nkhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran
  International Conference on Learning Representations (ICLR)

• Chils: Zero-shot image classification with hierarchical label sets

  Zachary Novack, Julian McAuley, Zachary Lipton, Saurabh Garg
  arXiv preprint arXiv:2302.02551

• RLSbench: Domain Adaptation Under Relaxed Label Shift

  Saurabh Garg, Nick Erickson, James Sharpnack, Alex Smola, Sivaraman Balakrishnan, Zachary Lipton
  arXiv preprint arXiv:2302.03020

• Factorial SDE for Multi-Output Gaussian Process Regression

  Daniel Jeong, Seyoung Kim
  International Conference on Artificial Intelligence and Statistics (AISTATS)

• Temporal Supervised Contrastive Learning with Applications to Tabular Time Series Data

  Shahriar Noroozizadeh, Jeremy Weiss, George Chen
  AAAI Workshop on Representation Learning for Responsible Human-Centric AI (R2HCAI)

• ET tu, CLIP? Addressing Common Object Errors for Unseen Environments

  Ye Won Byun*, Cathy Jiao*, Shahriar Noroozizadeh*, Jimin Sun*, Rosa Vitiello*
  Conference on Computer Vision and Pattern Recognition - Embodied AI Workshop

• Improving the Robustness of Summarization Models by Detecting and Removing Input Noise

  Kundan Krishna, Yao Zhao, Jie Ren, Balaji Lakshminarayanan, Jiaming Luo, Mohammad Saleh, Peter J. Liu
  arXiv (preprint)

• Assistive alignment of in-the-wild sheet music and performances

  Michael Feffer, Zachary Lipton, Chris Donahue
  23rd Int. Society for Music Information Retrieval Conf. (ISMIR LBD)

• Doubly Mixed-Effects Gaussian Process Regression

  Jun Ho Yoon, Daniel Jeong, Seyoung Kim
  International Conference on Artificial Intelligence and Statistics (AISTATS)

• Unsupervised Learning under Latent Label Shift

  Manley Roberts*, Pranav Mani*, Saurabh Garg, Zachary Lipton
  Advances in Neural Information Processing Systems (NeurIPS)

• Domain Adaptation under Open Set Label Shift

  Saurabh Garg, Sivaraman Balakrishnan, Zachary Lipton
  Advances in Neural Information Processing Systems (NeurIPS)

• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations

  Siddhant Arora*, Danish Pruthi*, Norman Sadeh, William Cohen, Zachary Lipton, Graham Neubig
  Association for the Advancement of Artificial Intelligence (AAAI)

• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

  Saurabh Garg, Sivaraman Balakrishnan, Zachary Lipton, Hanie Sedghi, Behnam Neyshabur
  International Conference on Learning Representations (ICLR)

• Mixture Proportion Estimation and PU Learning: A Modern Approach

  Saurabh Garg, Yifan Wu, Alex Smola, Sivaraman Balakrishnan, Zachary Lipton
  Advances in Neural Information Processing Systems (NeurIPS)

• Parametric Complexity Bounds for Approximating PDEs with Neural Networks

  Tanya Marwah, Zachary Lipton, Andrej Risteski
  Advances in Neural Information Processing Systems (NeurIPS)

• Does Pretraining for Summarization Require Knowledge Transfer?

  Kundan Krishna, Jeffrey Bigham, Zachary Lipton
  Findings of EMNLP

• Evaluating Explanations: How much do explanations from the teacher aid students?

  Danish Pruthi, Rachit Bansal, Bhuwan Dhingra, Livio Baldini Soares, Michael Collins, Zachary Lipton, Graham Neubig, William Cohen
  Transactions of the Association for Computational Linguistics (TACL)

• On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study

  Divyansh Kaushik, Douwe Kiela, Zachary Lipton, Wen-tau Yih
  Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP)

• Correcting Exposure Bias for Link Recommendation

  Shantanu Gupta, Hao Wang, Zachary Lipton, Yuyang Wang
  International Conference on Machine Learning (ICML)

• RATT: Leveraging Unlabeled Data to Guarantee Generalization

  Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter, Zachary Lipton
  International Conference on Machine Learning (ICML)

• On Proximal Policy Optimization’s Heavy-Tailed Gradients

  Saurabh Garg, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Zachary Lipton, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Pradeep Ravikumar
  International Conference on Machine Learning (ICML)

• Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability

  Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar
  International Conference on Learning Representations (ICLR)

• Do Context-Aware Translation Models Pay the Right Attention?

  Kayo Yin, Patrick Fernandes, Danish Pruthi, Aditi Chaudhary, André F. T. Martins, Graham Neubig
  Association for Computational Linguistics (ACL)

• Generating SOAP Notes from Doctor-Patient Conversations

  Kundan Krishna, Sopan Khosla, Jeffrey Bigham, Jeffrey Bigham
  Association for Computational Linguistics (ACL)

• Explaining The Efficacy of Counterfactually-Augmented Data

  Divyansh Kaushik, Zachary Lipton
  International Conference on Learning Representations (ICLR)

• Decoding and Diversity in Machine Translation

  Nick Roberts, Davis Liang, Graham Neubig, Zachary Lipton
  NeurIPS Resistance AI Workshop

• On Negative Interference in Multilingual Models:Findings and A Meta-Learning Treatment

  Zirui Wang, Yulia Tsvetkov, Zachary Lipton
  Empirical Methods in Natural Language Processing (EMNLP)

• Why and when should you pool? Analyzing Pooling in Recurrent Architectures

  Pratyush Maini, Keshav Kolluru, Danish Pruthi, Mausam
  Findings of EMNLP

• NeuSpell: A Neural Spelling Correction Toolkit

  Sai Muralidhar Jayanthi, Danish Pruthi, Graham Neubig
  EMNLP (Demo Track)

• A Unified View of Label Shift Estimation

  Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan, Zachary Lipton
  Advances in Neural Information Processing Systems (NeurIPS)

• Uncertainty-Aware Lookahead Factor Models for Quantitative Investing

  Lakshay Chauhan, John Alberg, Zachary Lipton
  International Conference on Machine Learning (ICML)

• Learning to Deceive with Attention-Based Explanations

  Danish Pruthi, Mansi Gupta, Bhuwan Dhingra, Graham Neubig, Zachary Lipton
  Association for Computational Linguistics (ACL)

• Analyzing Student Strategies In Blended Courses Using Clickstream Data

  Nil-Jana Akpinar, Aaditya Ramdas, Umut Acar
  Thirteenth International Conference on Educational Data Mining (EDM 2020)

• Learning the Difference that Makes a Difference with Counterfactually-Augmented Data

  Divyansh Kaushik, Zachary Lipton
  International Conference on Learning Representations (ICLR)

• Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks

  Shubham Sonawani, Ryan Alimo, Renuad Detry, Daniel Jeong, Andrew Hess, Heni Ben Amor
  AIAA SciTech

• COSMIC: Content-based Onboard Summarization to Monitor Infrequent Change

  Gary Doran, Erik Langert, Steven Lu, Lukas Mandrake, Kiri Wagstaff, Jimmie Young, Anneliese Braunegg, Paul Horton, Daniel Jeong, Asher Trockman
  IEEE Aerospace Conference

• Sample Complexity Bounds for Recurrent Neural Networks with Application to Combinatorial Graph Problems

  Nil-Jana Akpinar, Bernhard Kratzwald, Stefan Feuerriegel
  Thirty-Fourth Conference on Artifical Intelligence (AAAI 2020) (Student Abstract)

• Extracting Structured Data from Doctor-Patient Conversations by Predicting Noteworthy Utterances

  Kundan Krishna, Amy Pavel, Benjamin Schloss, Jeffrey Bigham, Zachary Lipton
  AAAI Workshop Health Intelligence

• Predicting Mortality in Liver Transplant Candidates

  Jonathon Byrd, Sivaraman Balakrishnan, Xiaoqian Jiang, Zachary Lipton
  AAAI Workshop Health Intelligence

• Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

  Simran Kaur, Jeremy Cohen, Zachary Lipton
  Neurips 2019 Science Meets Engineering of Deep Learning Workshop

• Learning Robust Global Representations by Penalizing Local Predictive Power

  Haohan Wang, Songwei Ge, Eric Xing, Zachary Lipton
  Advances in Neural Information Processing Systems (NeurIPS)

• Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift

  Stefan Rabanser, Stephan Günnemann, Zachary Lipton
  Advances in Neural Information Processing Systems (NeurIPS)

• Practical Obstacles to Deploying Active Learning

  David Lowell, Zachary Lipton, Byron Wallace
  Empirical Methods in Natural Language Processing (EMNLP)

• Entity Projection via Machine Translation for Cross-Lingual NER

  Alankar Jain, Bhargavi Paranjape, Zachary Lipton
  Empirical Methods in Natural Language Processing (EMNLP)

• AmazonQA: A Review-Based Question Answering Task

  Mansi Gupta, Nitish Kulkarni, Raghuveer Chanda, Anirudha Rayasam, Zachary Lipton
  International Joint Conference on Machine Learning (IJCAI)

• Embryo staging with weakly-supervised region selection and dynamically- decoded predictions

  Tingfung Lau, Nathan Ng, Julian Gingold, Nina Desai, Julian McAuley, Zachary Lipton
  Machine Learning for Healthcare (MLHC)

• Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment

  Yifan Wu, Divyansh Kaushik, Ezra Winston, Zachary Lipton
  International Conference on Machine Learning (ICML)

• What is the Effect of Importance Weighting in Deep Learning?

  Jonathon Byrd, Zachary Lipton
  International Conference on Machine Learning (ICML)

• Combating Adversarial Misspellings with Robust Word Recognition

  Danish Pruthi, Bhuwan Dhingra, Zachary Lipton
  Association for Computational Linguistics (ACL)

• Troubling Trends in Machine Learning Scholarship

  Zachary Lipton*, Jacob Steinhardt*
  Communications of the ACM (CACM)

• Reinforcement Learning with Unknown Reward Functions

  Benjamin Eysenbach*, Jacob Tyo*, Shane Gu, Ruslan Salakhutdinov, Zachary Lipton, Sergey Levine
  Task-Agnostic Reinforcement Learning Workshop, ICLR

• Learning Robust Representations by Projecting Superficial Statistics Out

  Haohan Wang, Zexue Hu, Zachary Lipton, Eric Xing
  International Conference on Learning Representations (ICLR)

• Active Learning with Partial Feedback

  Peiyun Hu, Zachary Lipton, Anima Anandkumar, Deva Ramanan
  International Conference on Learning Representations (ICLR)

• Protein structure prediction with deep learning representations

  Iddo Drori, Darshan Thaker, Arjun Srivatsa, Daniel Jeong, Yueqi Wang, Linyong Nan, Fan Wu, Dimitri Leggas, Jinhao Lei, Weiyi Lu, Weilong Fu, Yuan Gao, Sashank Karri, Anand Kannan, Antonio Moretti, Chen Keasar, Itsik Pe’er
  NeurIPS Learning Meaningful Representations of Life Workshop

• How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks

  Divyansh Kaushik, Zachary Lipton
  Empirical Methods in Natural Language Processing (EMNLP)

• Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study

  Aditya Siddhant, Zachary Lipton
  Empirical Methods in Natural Language Processing (EMNLP)

• Learning Noise-Invariant Representations for Robust Speech Recognition

  Davis Liang, Zhiheng Huang, Zachary Lipton
  IEEE Speech and Language Technology (SLT)

• Born Again Networks

  Tommaso Furlanello, Zachary Lipton, Michael Tschannen, Laurent Itti, Anima Anandkumar
  International Conference on Machine Learning (ICML)

• Detecting and Correcting for Label Shift with Black Box Predictors

  Zachary Lipton*, Yu-Xiang Wang*, Alex Smola
  International Conference on Machine Learning (ICML)

• Semantically Decomposing the Latent Spaces of Generative Adversarial Networks

  Chris Donahue, Zachary Lipton, Akshay Balsubramani, Julian McAuley
  International Conference on Learning Representations (ICLR)

• Stochastic Activation Pruning for Robust Adversarial Defense

  Guneet Dhillon Singh, Kamyar Azizzadenesheli, Jeremy Bernstein, Aran Khanna, Zachary Lipton, Anima Anandkumar
  International Conference on Learning Representations (ICLR)

• Learning from Noisy Singly-Labeled Data

  Ashish Khetan, Zachary Lipton, Anima Anandkumar
  International Conference on Learning Representations (ICLR)

• Deep Active Learning for Named Entity Recognition

  Yanyao Shen, Hyokun Yun, Zachary Lipton, Anima Anandkumar
  International Conference on Learning Representations (ICLR)

• SPINE: SParse Interpretable Neural Embeddings

  Danish Pruthi*, Anant Subramanian*, Harsh Jhamtani*, Taylor Berg-Kirkpatrick, Eduard Hovy
  Association for the Advancement of Artificial Intelligence (AAAI)

• Efficient exploration for dialogue policy learning with BBQ-networks

  Zachary Lipton, Xiujun Li, Jianfeng Gao, Lihong Li, Li Deng
  Association for the Advancement of Artificial Intelligence (AAAI)

• Dance Dance Convolution

  Chris Donahue, Zachary Lipton, Julian McAuley
  International Conference on Machine Learning (ICML)

• Predicting Surgery Duration with Neural Heteroscedastic Regression

  Nathan Ng, Julian McAuley, Charles Elkan, Zachary Lipton
  Machine Learning for Healthcare (MLHC)

• Context Matters: Refining Object Detection in Video with Recurrent Neural Networks

  Zachary Lipton, Subarna Tripathi, Serge Belongie, Truong Nguyen
  British Machine Vision Conference (BMVC)

• Modeling Missing Data in Clinical Time Series with RNNs

  Zachary Lipton, David Kale, Randall Wetzel
  Machine Learning for Healthcare (MLHC)

• Learning to Diagnose with LSTM Recurrent Neural Networks

  Zachary Lipton, David Kale*, Charles Elkan, Randall Wetzel
  International Conference on Learning Representations (ICLR)

• Playing the Imitation Game with deep learning

  Zachary Lipton, Charles Elkan
  IEEE Spectrum