Katrina Drozdov (Evtimova)

Deep Learning Researcher

Best Deep Learning Award presented by Yann LeCun

About

I recently defended my PhD thesis at the NYU Center for Data Science under the supervision of Yann LeCun. My research interests lie in deep learning and in particular self-supervised learning and representation learning.

Contact & Links

  1. ✉ kve216 at nyu.edu
  2. @stochasticdoggo
  3. Google Scholar
  4. LinkedIn
  5. Resume
News

  • Oct 2024. My reserach on emergent communication with adaptive compute at inference time was featured in the CDS Blog: "From Academia to Industry: How a 2018 Paper Foreshadowed OpenAI’s Latest Innovation".
  • Jul 2024. Excited to share that I defended my thesis: "Representation Learning with Regularized Energy-Based Models"! I am currently on the job market, looking for ML research roles. Open to discuss various kinds of opportunities!
  • Feb 2024. Serving as a reviewer at ICML 2024.
  • Nov 2023. Serving as a reviewer at AISTATS 2024.
  • Oct 2023. Serving as a reviewer at ICLR 2024.
  • Mar 2023. Serving as a reviewer at ICML 2023.
  • Jan 2023. Gave an invited talk on self-supervised learning at Prof. Leif Weatherby's course "Theory of the Digital".
  • Nov 2022. I'll be at NeurIPS 2022. Would love to chat about self-supervised learning, regularization, latent variable models, etc. If you're also around, do reach out.
  • Aug 2022. Sparse Coding with Multi-Layer Decoders using Variance Regularization is now published at TMLR!
  • Apr 2022. Selected as one of the Highlighted Reviewers at ICLR 2022.
  • Apr 2022. Serving as a reviewer at ICML 2022.
  • Oct 2021. Serving as a reviewer at ICLR 2022.
  • Sep 2021. Excited to be an organizer of the 2022 NYU AI School.
  • Jul 2021. Serving as a reviewer at NeurIPS 2021.
  • Mar 2021. Serving as a reviewer at ICML 2021.
  • Feb 2021. Serving as a reviewer at the Energy-based Models workshop at ICLR 2021.
  • Apr 2020. Happy to share that I passed my Depth Qualification Exam on the topic of "Energy based Learning & Regularized Latent Variable Models" with committee members Joan Bruna, Kyunghyun Cho, and Yann LeCun.
  • Jan 2020. Gave a talk at the CILVR seminar entitled "Self-supervised Learning & Sparse Overcomplete Representations of Visual Data".
  • Jan 2020. Looking forward to being a teaching assistant for Introduction to Machine Learning at Courant over the spring.
  • Feb 2019. Excited to share that I'll be interning at FAIR this summer.
  • Jan 2019. Happy to be a section leader for NYU's Deep Learning class this spring.

Publications

  • Evtimova, K., Shwartz-Ziv, R. and LeCun, Y. Video Representation Learning with Joint Embedding Predictive Architectures. In progress.
  • Zhu, J., Evtimova, K., Chen, Y., Shwartz-Ziv, R. and LeCun, Y. Variance-Covariance Regularization Improves Representation Learning. In submission, 2024. pdf
  • Evtimova, K. and LeCun, Y. Sparse Coding with Multi-Layer Decoders using Variance Regularization. Published in Transactions on Machine Learning Research, Aug 2022. pdf code
  • Evtimova, K., Drozdov, A., Kiela, D. and Cho, K. Emergent Communication in a Multi-Modal, Multi-Step Referential Game. Accepted as a poster at ICLR 2018. pdf code

Unpublished Work

  • Katrina Evtimova, 2020. Sparse and Overcomplete Image Representations. pdf
  • Katrina Evtimova, Andrew Drozdov, 2016. Understanding Mutual Information and its Use in InfoGAN. pdf code (won Best Deep Learning Project Award at the CDS Student Awards Ceremony in February 2017)

Blog template built by @mdo.