Anish Chakrabarty

Tagline:Senior Research Fellow at Indian Statistical Institute, Kolkata

Kolkata, West Bengal, India

personal photo of Anish Chakrabarty

About Me

I am a final-year PhD student in the Theoretical Statistics and Mathematics Unit at Indian Statistical Institute (ISI) Kolkata, where I am advised by Prof. Swagatam Das and Prof. Probal Chaudhuri. Before joining ISI, I received a Master of Science in Statistics from the Indian Institute of Technology, Kanpur (IITK).

I am broadly interested in statistical learning theory and high-dimensional statistics. I have recently worked on topics in the following areas: Optimal transport, deep generative models, robust statistics, and theory of attention. Some of my recent work is motivated by problems arising in computer vision and shape matching.

My papers can be found below or on my Google Scholar page.

❄️ I am an organizing committee member of the Winter School on Deep Learning, hosted annually by the Machine Learning Research Group, which I am also a part of.

News

Preprints

  • Relation-Aware Slicing in Cross-Domain Alignment

    From: 2025

    Dhruv Sarkar • Aprameyo Chakrabartty • Anish Chakrabarty • Swagatam Das

    arXiv

  • On the Existence of Universal Simulators of Attention

    From: 2025

    Debanjan Dutta • Faizanuddin Ansari • Anish Chakrabarty • Swagatam Das

    arXiv

  • On Robust Cross Domain Alignment

    From: 2024

    Anish Chakrabarty • Arkaprabha Basu • Swagatam Das

    arXiv

  • Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution

    From: 2024

    Arkaprabha Basu • Kushal Bose • Sankha Subhra Mullick • Anish Chakrabarty • Swagatam Das

    arXiv

Publications

  • Locally Robust Alignment Between Distinct Spaces

    Journal ArticlePublisher:StatDate:2025
    Authors:
    Anish ChakrabartySankha Subhra MullickSwagatam Das
    Paper

  • Information Preservation with Wasserstein Autoencoders: Generation Consistency and Adversarial Robustness

    Journal ArticlePublisher:Statistics and ComputingDate:2025
    Authors:
    Anish ChakrabartyArkaprabha BasuSwagatam Das
    Paper

  • Lost in Translation: GANs' Inability to Generate Simple Probability Distributions

    Conference PaperPublisher:ICLR Tiny Papers TrackDate:2024
    Authors:
    Debanjan DuttaAnish ChakrabartySwagatam Das
    Description:

    (Notable)

    OpenReview

  • Enhancing Contrastive Clustering with Negative Pair-guided Regularization

    Journal ArticlePublisher:TMLRDate:2024
    Authors:
    Abhishek KumarAnish ChakrabartySankha Subhra MullickSwagatam Das

  • Interval Bound Interpolation for Few-shot Learning with Few Tasks

    Conference PaperPublisher:ICMLDate:2023
    Authors:
    Shounak DattaSankha Subhra MullickAnish ChakrabartySwagatam Das
    Paper

  • On strong consistency of kernel k-means: A Rademacher complexity approach

    Journal ArticlePublisher:Statistics & Probability LettersDate:2022
    Authors:
    Anish ChakrabartySwagatam Das
    Paper

  • On Translation and Reconstruction Guarantees of the Cycle-Consistent Generative Adversarial Networks

    Conference PaperPublisher:NeurIPSDate:2022
    Authors:
    Anish ChakrabartySwagatam Das
    Paper

  • Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency

    Conference PaperPublisher:NeurIPSDate:2021
    Authors:
    Anish ChakrabartySwagatam Das
    Description:

    (Spotlight)

    Paper

Curriculum Vitae (CV)

Download

Contact

  • Email: chakrabarty.anish@gmail.com
  • Office address: 203 B. T. Road, Indian Statistical Institute Kolkata 700108