default search action
Kush Bhatia
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c22]Michael Zhang, Kush Bhatia, Hermann Kumbong, Christopher Ré:
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry. ICLR 2024 - [i25]Michael Zhang, Kush Bhatia, Hermann Kumbong, Christopher Ré:
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry. CoRR abs/2402.04347 (2024) - [i24]Avanika Narayan, Mayee F. Chen, Kush Bhatia, Christopher Ré:
Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates. CoRR abs/2410.05224 (2024) - [i23]Vishnu Sarukkai, Brennan Shacklett, Zander Majercik, Kush Bhatia, Christopher Ré, Kayvon Fatahalian:
Automated Rewards via LLM-Generated Progress Functions. CoRR abs/2410.09187 (2024) - 2023
- [c21]Kush Bhatia, Wenshuo Guo, Jacob Steinhardt:
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws. AISTATS 2023: 11149-11171 - [c20]Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel J. Orr, Neel Guha, Kush Bhatia, Ines Chami, Christopher Ré:
Ask Me Anything: A simple strategy for prompting language models. ICLR 2023 - [c19]Joey Hong, Kush Bhatia, Anca D. Dragan:
On the Sensitivity of Reward Inference to Misspecified Human Models. ICLR 2023 - [c18]Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré:
TART: A plug-and-play Transformer module for task-agnostic reasoning. NeurIPS 2023 - [c17]Mayee F. Chen, Nicholas Roberts, Kush Bhatia, Jue Wang, Ce Zhang, Frederic Sala, Christopher Ré:
Skill-it! A data-driven skills framework for understanding and training language models. NeurIPS 2023 - [c16]Neel Guha, Mayee F. Chen, Kush Bhatia, Azalia Mirhoseini, Frederic Sala, Christopher Ré:
Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification. NeurIPS 2023 - [c15]Sarah M. Hooper, Mayee F. Chen, Khaled Saab, Kush Bhatia, Curtis P. Langlotz, Christopher Ré:
A case for reframing automated medical image classification as segmentation. NeurIPS 2023 - [i22]Pranjal Awasthi, Kush Bhatia, Sreenivas Gollapudi, Kostas Kollias:
Congested Bandits: Optimal Routing via Short-term Resets. CoRR abs/2301.09251 (2023) - [i21]Kush Bhatia, Wenshuo Guo, Jacob Steinhardt:
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws. CoRR abs/2302.12349 (2023) - [i20]Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré:
TART: A plug-and-play Transformer module for task-agnostic reasoning. CoRR abs/2306.07536 (2023) - [i19]Neel Guha, Mayee F. Chen, Kush Bhatia, Azalia Mirhoseini, Frederic Sala, Christopher Ré:
Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification. CoRR abs/2307.11031 (2023) - [i18]Mayee F. Chen, Nicholas Roberts, Kush Bhatia, Jue Wang, Ce Zhang, Frederic Sala, Christopher Ré:
Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models. CoRR abs/2307.14430 (2023) - [i17]Gabriel Mukobi, Peter Chatain, Su Fong, Robert Windesheim, Gitta Kutyniok, Kush Bhatia, Silas Alberti:
SuperHF: Supervised Iterative Learning from Human Feedback. CoRR abs/2310.16763 (2023) - 2022
- [b1]Kush Bhatia:
Learning when Objectives are Hard to Specify. University of California, Berkeley, USA, 2022 - [c14]Alexander Pan, Kush Bhatia, Jacob Steinhardt:
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. ICLR 2022 - [c13]Pranjal Awasthi, Kush Bhatia, Sreenivas Gollapudi, Kostas Kollias:
Congested Bandits: Optimal Routing via Short-term Resets. ICML 2022: 1078-1100 - [i16]Alexander Pan, Kush Bhatia, Jacob Steinhardt:
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models. CoRR abs/2201.03544 (2022) - [i15]Kush Bhatia, Nikki Lijing Kuang, Yi-An Ma, Yixin Wang:
Statistical and Computational Trade-offs in Variational Inference: A Case Study in Inferential Model Selection. CoRR abs/2207.11208 (2022) - [i14]Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel J. Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, Christopher Ré:
Ask Me Anything: A simple strategy for prompting language models. CoRR abs/2210.02441 (2022) - [i13]Joey Hong, Kush Bhatia, Anca D. Dragan:
On the Sensitivity of Reward Inference to Misspecified Human Models. CoRR abs/2212.04717 (2022) - 2021
- [c12]Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt:
Agnostic Learning with Unknown Utilities. ITCS 2021: 55:1-55:20 - [i12]Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt:
Agnostic learning with unknown utilities. CoRR abs/2104.08482 (2021) - [i11]Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright:
Preference learning along multiple criteria: A game-theoretic perspective. CoRR abs/2105.01850 (2021) - 2020
- [j2]Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright:
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. J. Mach. Learn. Res. 21: 21:1-21:51 (2020) - [c11]Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, Martin J. Wainwright:
Preference learning along multiple criteria: A game-theoretic perspective. NeurIPS 2020 - [c10]Kush Bhatia, Karthik Sridharan:
Online learning with dynamics: A minimax perspective. NeurIPS 2020 - [i10]Kush Bhatia, Karthik Sridharan:
Online learning with dynamics: A minimax perspective. CoRR abs/2012.01705 (2020)
2010 – 2019
- 2019
- [c9]Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright:
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. AISTATS 2019: 2916-2925 - [c8]Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain:
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression. COLT 2019: 2892-2897 - [c7]Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, Gellért Weisz:
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction. ICML 2019: 3692-3702 - [i9]Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma:
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network. CoRR abs/1901.02358 (2019) - [i8]Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain:
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression. CoRR abs/1903.08192 (2019) - [i7]Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, Michael I. Jordan:
Bayesian Robustness: A Nonasymptotic Viewpoint. CoRR abs/1907.11826 (2019) - 2018
- [c6]Sandy H. Huang, Kush Bhatia, Pieter Abbeel, Anca D. Dragan:
Establishing Appropriate Trust via Critical States. IROS 2018: 3929-3936 - [c5]Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan:
Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation. NeurIPS 2018: 7016-7025 - [c4]Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma:
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network. NeurIPS 2018: 9031-9042 - [i6]Sandy H. Huang, Kush Bhatia, Pieter Abbeel, Anca D. Dragan:
Establishing Appropriate Trust via Critical States. CoRR abs/1810.08174 (2018) - [i5]Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, Michael I. Jordan:
Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation. CoRR abs/1811.08393 (2018) - [i4]Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright:
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. CoRR abs/1812.08305 (2018) - 2017
- [c3]Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar:
Consistent Robust Regression. NIPS 2017: 2110-2119 - 2016
- [j1]Dinesh Khandelwal, Kush Bhatia, Chetan Arora, Parag Singla:
Lazy Generic Cuts. Comput. Vis. Image Underst. 143: 80-91 (2016) - [i3]Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar:
Efficient and Consistent Robust Time Series Analysis. CoRR abs/1607.00146 (2016) - 2015
- [c2]Kush Bhatia, Prateek Jain, Purushottam Kar:
Robust Regression via Hard Thresholding. NIPS 2015: 721-729 - [c1]Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, Prateek Jain:
Sparse Local Embeddings for Extreme Multi-label Classification. NIPS 2015: 730-738 - [i2]Kush Bhatia, Prateek Jain, Purushottam Kar:
Robust Regression via Hard Thresholding. CoRR abs/1506.02428 (2015) - [i1]Kush Bhatia, Himanshu Jain, Purushottam Kar, Prateek Jain, Manik Varma:
Locally Non-linear Embeddings for Extreme Multi-label Learning. CoRR abs/1507.02743 (2015)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-25 22:43 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: