Nikunj Saunshi

Citirano

	Sve	Od 2019.
Citati	1886	1850
H-indeks	14	14
i10-indeks	15	15

520

260

130

390

201820192020202120222023202431 75 166 261 442 518 387

Javni pristup

Prikaži sve

10 članaka

0 članaka

dostupno

nije dostupno

Na temelju uvjeta financiranja

Suautori

Sanjeev AroraProfessor of Computer Science, Princeton UniversityPotvrđena adresa e-pošte na cs.princeton.edu
Mikhail KhodakCMUPotvrđena adresa e-pošte na cs.princeton.edu
Hrishikesh KhandeparkarQuantitative Researcher, Citadel SecuritiesPotvrđena adresa e-pošte na alumni.princeton.edu
Kiran VodrahalliResearch Scientist, Google DeepMindPotvrđena adresa e-pošte na google.com
Arushi GuptaPhD Student, Princeton UniversityPotvrđena adresa e-pošte na princeton.edu
Sham M KakadeHarvard UniversityPotvrđena adresa e-pošte na seas.harvard.edu
Cyril ZhangMicrosoft AIPotvrđena adresa e-pošte na microsoft.com
Jason D. LeeAssociate Professor of Electrical Engineering and Computer Science, Princeton UniversityPotvrđena adresa e-pošte na princeton.edu
Qi LeiAssistant Professor of Mathematics and Data Science, New York UniversityPotvrđena adresa e-pošte na nyu.edu
Jiacheng ZhuoUniversity of Texas at AustinPotvrđena adresa e-pošte na utexas.edu
Brandon M. StewartPrinceton UniversityPotvrđena adresa e-pošte na princeton.edu
Tengyu MAStanford UniversityPotvrđena adresa e-pošte na stanford.edu
Abhishek PanigrahiGraduate Student, Princeton UniversityPotvrđena adresa e-pošte na princeton.edu
Surbhi GoelAssistant Professor, University of PennsylvaniaPotvrđena adresa e-pošte na cis.upenn.edu
Dipendra MisraStaff Research Scientist, Mosaic Team, DatabricksPotvrđena adresa e-pošte na databricks.com
Jordan T. AshMicrosoft Research NYCPotvrđena adresa e-pošte na princeton.edu
Akshay KrishnamurthyUniversity of Massachusetts AmherstPotvrđena adresa e-pošte na cs.umass.edu
Yi ZhangSenior Researcher at Microsoft Research RedmondPotvrđena adresa e-pošte na microsoft.com
Sadhika MalladiPrinceton UniversityPotvrđena adresa e-pošte na princeton.edu
Simon Shaolei DuAssistant Professor, School of Computer Science and Engineering, University of WashingtonPotvrđena adresa e-pošte na cs.washington.edu

Prati

Nikunj Saunshi

Research Scientist, Google

Potvrđena adresa e-pošte na google.com - Početna stranica

Machine Learning Artificial Intelligence Natural Language Processing


Naslov Poredaj po navodima Poredaj po godini Poredaj po naslovu	Citirano Citirano	Godina
A Theoretical Analysis of Contrastive Unsupervised Representation Learning S Arora, H Khandeparkar, M Khodak, O Plevrakis, N Saunshi International Conference on Machine Learning (ICML) 2019, 2019	812*	2019
A Large Self-Annotated Corpus for Sarcasm M Khodak, N Saunshi, K Vodrahalli Language Resources and Evaluation Conference (LREC) 2018, 2017	275	2017
Predicting What You Already Know Helps: Provable Self-Supervised Learning JD Lee, Q Lei, N Saunshi, J Zhuo Neural Information Processing Systems (NeurIPS) 2021, 2020	185	2020
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors M Khodak, N Saunshi, Y Liang, T Ma, B Stewart, S Arora Association for Computational Linguistics (ACL) 2018, 2018	126	2018
Understanding Contrastive Learning Requires Incorporating Inductive Biases N Saunshi, J Ash, S Goel, D Misra, C Zhang, S Arora, S Kakade, ... International Conference on Machine Learning (ICML) 2022, 2022	108	2022
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks N Saunshi, S Malladi, S Arora International Conference on Learning Representations (ICLR) 2021, 2020	83	2020
Provable representation learning for imitation learning via bi-level optimization S Arora, S Du, S Kakade, Y Luo, N Saunshi International Conference on Machine Learning (ICML) 2020, 2020	66	2020
A compressed sensing view of unsupervised text embeddings, bag-of-n-grams, and LSTMs S Arora, M Khodak, N Saunshi, K Vodrahalli International Conference on Learning Representations (ICLR) 2018, 2018	52	2018
Task-Specific Skill Localization in Fine-tuned Language Models A Panigrahi, N Saunshi, H Zhao, S Arora International Conference on Machine Learning (ICML) 2023, 2023	48	2023
A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning N Saunshi, A Gupta, W Hu International Conference on Machine Learning (ICML) 2021, 2021	26	2021
A sample complexity separation between non-convex and convex meta-learning N Saunshi, Y Zhang, M Khodak, S Arora International Conference on Machine Learning (ICML) 2020, 2020	24	2020
Reasoning in Large Language Models Through Symbolic Math Word Problems V Gaur, N Saunshi Findings of the Association for Computational Linguistics (ACL) 2023, 2023	22	2023
Understanding Influence Functions and Datamodels via Harmonic Analysis N Saunshi, A Gupta, M Braverman, S Arora International Conference on Learning Representations (ICLR) 2023, 2022	15	2022
On Predicting Generalization using GANs Y Zhang, A Gupta, N Saunshi, S Arora International Conference on Learning Representations (ICLR) 2022, 2021	14	2021
Pixie: a social chatbot O Adewale, A Beatson, D Buniatyan, J Ge, M Khodak, H Lee, N Prasad, ... Alexa prize proceedings, 2017	14	2017
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound A Gupta, N Saunshi, D Yu*, K Lyu, S Arora Neural Information Processing Systems (NeurIPS) 2022, 2021	7	2021
Method and apparatus for system resource management YU Changhun, KIM Wonjin, H Kim, M Sunho, AHN Minwook, R Kim, ... US Patent 10,474,574, 2019	5	2019
Towards Understanding Self-Supervised Representation Learning N Saunshi PhD Thesis, 2022	2	2022
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? K Gatmiry, N Saunshi, SJ Reddi, S Jegelka, S Kumar Forty-first International Conference on Machine Learning, 2024	1	2024
Efficient Stagewise Pretraining via Progressive Subnetworks A Panigrahi, N Saunshi, K Lyu, S Miryoosefi, S Reddi, S Kale, S Kumar arXiv preprint arXiv:2402.05913, 2024	1	2024

Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.

Članci 1–20

Godišnji broj citata

Dvostruki navodi

Spojeni navodi

Dodavanje suautoraSuautori

Prati

Citirano

Suautori