Sivakanth Gopi

CoRR, September, 2025

On the Emergence of Thinking in LLMs I: Searching for the Right Intuition.

[BibT_eX]

[DOI]

CoRR, February, 2025

Tensor Concentration Inequalities: A Geometric Approach.

[BibT_eX]

[DOI]

Proceedings of the 57th Annual ACM Symposium on Theory of Computing, 2025

DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory.

[BibT_eX]

[DOI]

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

2024

Selective Pre-training for Private Fine-tuning.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2024

A Geometric Perspective on the Injective Norm of Sums of Random Tensors.

[BibT_eX]

[DOI]

CoRR, 2024

Ranking with Multiple Objectives.

[BibT_eX]

[DOI]

Nikhil R. Devanur

CoRR, 2024

Rigidity matroids and linear algebraic matroids with applications to matrix completion and tensor codes.

[BibT_eX]

[DOI]

CoRR, 2024

AG Codes Achieve List Decoding Capacity over Constant-Sized Fields.

[BibT_eX]

[DOI]

Proceedings of the 56th Annual ACM Symposium on Theory of Computing, 2024

Generalized GM-MDS: Polynomial Codes Are Higher Order MDS.

[BibT_eX]

[DOI]

Fatemehsadat Mireshghallah

Proceedings of the 56th Annual ACM Symposium on Theory of Computing, 2024

Differentially Private Synthetic Data via Foundation Model APIs 2: Text.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Differentially Private Synthetic Data via Foundation Model APIs 1: Images.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

AG codes achieve list decoding capacity over contant-sized fields.

[BibT_eX]

[DOI]

CoRR, 2023

Textbooks Are All You Need.

[BibT_eX]

[DOI]

Suriya Gunasekar

Yi Zhang

Jyoti Aneja

Caio César Teodoro Mendes

CoRR, 2023

Generic Reed-Solomon Codes Achieve List-Decoding Capacity.

[BibT_eX]

[DOI]

Visu Makam

Proceedings of the 55th Annual ACM Symposium on Theory of Computing, 2023

Private Convex Optimization in General Norms.

[BibT_eX]

[DOI]

Proceedings of the 2023 ACM-SIAM Symposium on Discrete Algorithms, 2023

A construction of Maximally Recoverable LRCs for small number of local groups.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2023

Improved Field Size Bounds for Higher Order MDS Codes.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Information Theory, 2023

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Lower Bounds for Maximally Recoverable Tensor Codes and Higher Order MDS Codes.

[BibT_eX]

[DOI]

Visu Makam

IEEE Trans. Inf. Theory, 2022

Constraint Satisfaction Problems with Global Modular Constraints: Algorithms and Hardness via Polynomial Representations.

[BibT_eX]

[DOI]

SIAM J. Comput., 2022

Differentially Private Fine-tuning of Language Models.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Private Convex Optimization via Exponential Mechanism.

[BibT_eX]

[DOI]

Yin Tat Lee

Daogao Liu

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Improved Maximally Recoverable LRCs using Skew Polynomials.

[BibT_eX]

[DOI]

Electron. Colloquium Comput. Complex., 2021

Lower Bounds for Maximally Recoverable Tensor Code and Higher Order MDS Codes.

[BibT_eX]

[DOI]

Visu Makam

CoRR, 2021

Differentially Private n-gram Extraction.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Numerical Composition of Differential Privacy.

[BibT_eX]

[DOI]

Sundara Rajan Srinivasavaradhan

Yin Tat Lee

Lukas Wutschitz

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Fast and Memory Efficient Differentially Private-SGD via JL Projections.

[BibT_eX]

[DOI]

Uthaipon Tantipongpipat

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Trellis BMA: Coded Trace Reconstruction on IDS Channels for DNA Storage.

[BibT_eX]

[DOI]

Henry D. Pfister

Sergey Yekhanin

Proceedings of the IEEE International Symposium on Information Theory, 2021

2020

Differentially Private Set Union.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Locally Private Hypothesis Selection.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2020

2019

CSPs with global modular constraints: algorithms and hardness via polynomial representations.

[BibT_eX]

[DOI]

Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, 2019

Maximally Recoverable LRCs: A field size lower bound and constructions for few heavy parities.

[BibT_eX]

[DOI]

Sergey Yekhanin

Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, 2019

Spanoids - An Abstraction of Spanning Structures, and a Barrier for LCCs.

[BibT_eX]

[DOI]

Proceedings of the 10th Innovations in Theoretical Computer Science Conference, 2019

2018

Locality in coding theory

[BibT_eX]

[DOI]

PhD thesis, 2018

Optimal Instance Adaptive Algorithm for the Top-K Ranking Problem.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2018

Spanoids - an abstraction of spanning structures, and a barrier for LCCs.

[BibT_eX]

[DOI]

Avi Wigderson

CoRR, 2018

2017

On Maximally Recoverable Local Reconstruction Codes.

[BibT_eX]

[DOI]

Sergey Yekhanin

Electron. Colloquium Comput. Complex., 2017

Gaussian width bounds with applications to arithmetic progressions in random settings.

[BibT_eX]

[DOI]

Jop Briët

CoRR, 2017

Locally Testable and Locally Correctable Codes Approaching the Gilbert-Varshamov Bound.

[BibT_eX]

[DOI]

Rafael Mendes de Oliveira

Swastik Kopparty

Noga Ron-Zewi

Shubhangi Saraf

Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, 2017

Competitive analysis of the top-<i>K</i> ranking problem.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete Algorithms, 2017

Outlaw Distributions and Locally Decodable Codes.

[BibT_eX]

[DOI]

Jop Briët

Proceedings of the 8th Innovations in Theoretical Computer Science Conference, 2017

Lower Bounds for 2-Query LCCs over Large Alphabet.

[BibT_eX]

[DOI]

Arnab Bhattacharyya

Avishay Tal

Proceedings of the Approximation, 2017

2016

2-Server PIR with Subpolynomial Communication.

[BibT_eX]

[DOI]

J. ACM, 2016

Lower bounds for 2-query LCCs over large alphabet.

[BibT_eX]

[DOI]

Arnab Bhattacharyya

Electron. Colloquium Comput. Complex., 2016

Competitive analysis of the top-K ranking problem.

[BibT_eX]

[DOI]

CoRR, 2016

Lower Bounds for Constant Query Affine-Invariant LCCs and LTCs.

[BibT_eX]

[DOI]

Arnab Bhattacharyya

Proceedings of the 31st Conference on Computational Complexity, 2016

2015

2-Server PIR with Sub-Polynomial Communication.

[BibT_eX]

[DOI]

Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing, 2015

On the Number of Rich Lines in Truly High Dimensional Sets.

[BibT_eX]

[DOI]