Kush Bhatia

According to our database, Kush Bhatia authored at least 30 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry.

Michael Zhang, Kush Bhatia, Hermann Kumbong, Christopher Ré

CoRR, 2024

2023

SuperHF: Supervised Iterative Learning from Human Feedback.

Gabriel Mukobi, Peter Chatain, Su Fong, Robert Windesheim, Gitta Kutyniok, Kush Bhatia, Silas Alberti

CoRR, 2023

A case for reframing automated medical image classification as segmentation.

Sarah M. Hooper, Mayee F. Chen, Khaled Saab, Kush Bhatia, Curtis P. Langlotz, Christopher Ré

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification.

Neel Guha, Mayee F. Chen, Kush Bhatia, Azalia Mirhoseini, Frederic Sala, Christopher Ré

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Skill-it! A data-driven skills framework for understanding and training language models.

Mayee F. Chen, Nicholas Roberts, Kush Bhatia, Jue Wang, Ce Zhang, Frederic Sala, Christopher Ré

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

TART: A plug-and-play Transformer module for task-agnostic reasoning.

Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the Sensitivity of Reward Inference to Misspecified Human Models.

Joey Hong, Kush Bhatia, Anca D. Dragan

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Ask Me Anything: A simple strategy for prompting language models.

Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel J. Orr, Neel Guha, Kush Bhatia, Ines Chami, Christopher Ré

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws.

Kush Bhatia, Wenshuo Guo, Jacob Steinhardt

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Learning when Objectives are Hard to Specify

Kush Bhatia

PhD thesis, 2022

Ask Me Anything: A simple strategy for prompting language models.

Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel J. Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, Christopher Ré

CoRR, 2022

Statistical and Computational Trade-offs in Variational Inference: A Case Study in Inferential Model Selection.

Kush Bhatia, Nikki Lijing Kuang, Yi-An Ma, Yixin Wang

CoRR, 2022

Congested Bandits: Optimal Routing via Short-term Resets.

Pranjal Awasthi, Kush Bhatia, Sreenivas Gollapudi, Kostas Kollias

Proceedings of the International Conference on Machine Learning, 2022

The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

Alexander Pan, Kush Bhatia, Jacob Steinhardt

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Agnostic Learning with Unknown Utilities.

Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt

Proceedings of the 12th Innovations in Theoretical Computer Science Conference, 2021

2020

Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems.

Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright

J. Mach. Learn. Res., 2020

Online learning with dynamics: A minimax perspective.

Kush Bhatia, Karthik Sridharan

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Preference learning along multiple criteria: A game-theoretic perspective.

Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Bayesian Robustness: A Nonasymptotic Viewpoint.

Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, Michael I. Jordan

CoRR, 2019

Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression.

Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain

Proceedings of the Conference on Learning Theory, 2019

2018

Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation.

Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan

CoRR, 2018

FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network.

Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation.

Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Establishing Appropriate Trust via Critical States.

Sandy H. Huang, Kush Bhatia, Pieter Abbeel, Anca D. Dragan

Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018

2017

Consistent Robust Regression.

Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2016

Lazy Generic Cuts.

Dinesh Khandelwal, Kush Bhatia, Chetan Arora, Parag Singla

Comput. Vis. Image Underst., 2016

Efficient and Consistent Robust Time Series Analysis.

Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar

CoRR, 2016

2015

Locally Non-linear Embeddings for Extreme Multi-label Learning.

Kush Bhatia, Himanshu Jain, Purushottam Kar, Prateek Jain, Manik Varma

CoRR, 2015

Sparse Local Embeddings for Extreme Multi-label Classification.

Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, Prateek Jain

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Robust Regression via Hard Thresholding.

Kush Bhatia, Prateek Jain, Purushottam Kar

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015