PUBLICATIONS   CV   

= indicates alphabetical ordering, as is convention in theoretical computer science.
* indicates equal first-authorship

Preprints/In preparation

  1. Batch List-Decodable Linear Regression via Higher Moments
    Ilias Diakonikolas= , Daniel M. Kane= , Sushrut Karmalkar= , Sihan Liu = and Thanasis Pittas=

Publications

  1. Sum-of-Squares Lower Bounds for Non-Gaussian Component Analysis
    Ilias Diakonikolas=, Sushrut Karmalkar=, Shuo Pang= and Aaron Potechin=
    IEEE Symposium on Foundations of Computer Science (FOCS) 2024
  2. Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination
    Ilias Diakonikolas= , Daniel M. Kane= , Sushrut Karmalkar= , Ankit Pensia= and Thanasis Pittas=
    International Conference on Machine Learning (ICML) 2024
  3. Multi-Model 3D Registration: Finding Multiple Moving Objects in Cluttered Point Clouds
    David Jin, Sushrut Karmalkar, Harry Zhang and Luca Carlone
    IEEE International Conference on Robotics and Automation (ICRA) 2024
    [arxiv]
    [Note: Not alphabetical ordering]
  4. First Order Stochastic Optimization with Oblivious Noise
    Ilias Diakonikolas= , Sushrut Karmalkar= , Jongho Park= and Christos Tzamos=
    Neural Information Processing Systems (NeurIPS) 2023
    [paper]
  5. Distribution-Independent Regression for Generalized Linear Models with Oblivious Corruptions
    Ilias Diakonikolas= , Sushrut Karmalkar= , Jongho Park= and Christos Tzamos=
    Proceedings of the 36th Annual Conference on Learning Theory (COLT) 2023
    [arxiv]
  6. List-Decodable Sparse Mean Estimation via Difference-of-Pairs Filtering
    Ilias Diakonikolas= , Daniel M. Kane= , Sushrut Karmalkar= , Ankit Pensia= and Thanasis Pittas=
    Neural Information Processing Systems (NeurIPS) 2022 (Oral)
    [arxiv]
  7. Robust Sparse Mean Estimation via Sum of Squares
    Ilias Diakonikolas= , Daniel M. Kane= , Sushrut Karmalkar= , Ankit Pensia= and Thanasis Pittas=
    Conference on Learning Theory (COLT) 2022
    [arxiv]
  8. Fairness for Image Generation with Uncertain Sensitive Attributes
    Ajil Jalal*, Sushrut Karmalkar*, Jessica Hoffmann*, Alexandros G Dimakis and Eric Price
    International Conference on Machine Learning (ICML) 2021
    [Note: * indicates equal contribution]
    [arxiv] [Code]
  9. Instance-Optimal Compressed Sensing via Posterior Sampling
    Ajil Jalal, Sushrut Karmalkar, Alexandros G Dimakis and Eric Price
    International Conference on Machine Learning (ICML) 2021
    [Note: Not alphabetical ordering]
    [arxiv] [Code]
  10. Approximation Schemes for ReLU Regression
    Ilias Diakonikolas= , Surbhi Goel= , Sushrut Karmalkar= , Adam Klivans= and Mahdi Soltanolkotabi=
    Conference on Learning Theory (COLT) 2020
    [arxiv]
  11. Robustly Learning any Clusterable Mixture of Gaussians
    Ilias Diakonikolas= , Samuel B. Hopkins= , Daniel Kane= and Sushrut Karmalkar=
    IEEE Symposium on Foundations of Computer Science (FOCS) 2020
    [Note: Conference paper to be merged with this paper.]
    [arxiv] [Joint Talk @ FOCS]
  12. On the Power of Compressed Sensing with Generative Models
    Akshay Kamath= , Sushrut Karmalkar= and Eric Price=
    International Conference on Machine Learning (ICML) 2020
    [arxiv]
  13. Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent
    Surbhi Goel= , Aravind Gollakota= , Zhihan Jin= , Sushrut Karmalkar= and Adam Klivans=
    International Conference on Machine Learning (ICML) 2020
    [arxiv]
  14. Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
    Surbhi Goel= , Sushrut Karmalkar= and Adam Klivans=
    Neural Information Processing Systems (NeurIPS) 2019 (Spotlight)
    [arxiv]
  15. List decodeable linear regression
    Sushrut Karmalkar= , Adam Klivans= and Pravesh Kothari=
    Neural Information Processing Systems (NeurIPS) 2019 (Spotlight)
    [arxiv]
  16. Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering.
    Ilias Diakonikolas= , Daniel Kane= , Sushrut Karmalkar= , Eric Price= and Alistair Stewart=
    Neural Information Processing Systems (NeurIPS) 2019
    [arxiv] [Code]
  17. Compressed Sensing with Adversarial Sparse Noise via L1 Regression.
    Sushrut Karmalkar= and Eric Price=
    Symposium on Simplicity in Algorithms (SOSA) 2019
    [arxiv]
  18. Fourier Entropy-Influence Conjecture for Random Linear Threshold Functions
    Sourav Chakraborty= , Sushrut Karmalkar= , Srijita Kundu= , Satyanarayana V. Lokam= and Nitin Saurabh=
    Latin American Symposium on Theoretical Informatics (LATIN) 2018
    [arxiv]
  19. Robust Polynomial Regression up to the Information Theoretic Limit
    Daniel Kane= , Sushrut Karmalkar= and Eric Price=
    IEEE Symposium on Foundations of Computer Science (FOCS) 2017
    [arxiv]