Polina Kirichenko

I am a PhD candidate at New York University Center for Data Science working with professor Andrew Gordon Wilson. I am also a Visiting Researcher at FAIR Labs (Meta AI) working with Mark Ibrahim and Diane Bouchacourt. During my PhD, I interned at Meta AI, Google DeepMind and Cold Spring Harbor Laboratory. I received a BS in Computer Science at Higher School of Economics where I worked with professor Dmitry Vetrov. I was also a visiting research student at EPFL with professors Martin Jaggi and Dan Alistarh. I am a recipient of the Google Generation Scholarship and the DeepMind fellowship.

My research focuses on building trustworthy and reliable machine learning models. In particular, I am interested in:

• Robustness to distribution shifts and out-of-distribution generalization;
• Fairness and addressing biases in models and data;
• Out-of-distribution detection, uncertainty estimation and calibration;
• Understanding generalization and representations learning mechanisms in neural networks.

If you are an undergraduate or masters student interested in collaborating on research projects or looking for advice on PhD applications, please reach out!

Publications

• Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced Global Data?
  Megan Richards, Polina Kirichenko, Diane Bouchacourt, Mark Ibrahim
  ICML Data-centric Machine Learning Research Workshop, 2023;
  International Conference on Learning Representations (ICLR), 2024
  [arXiv]
• Understanding the Detrimental Class-level Effects of Data Augmentation
  Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Rama Vedantam, Hamed Firooz, Andrew Gordon Wilson
  ICML workshop on Spurious Correlations, Invariance, and Stability, 2023;
  Neural Information Processing Systems (NeurIPS), 2023
  [arXiv]
• Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
  Polina Kirichenko*, Pavel Izmailov*, Andrew Gordon Wilson
  ICML workshop on Spurious Correlations, Invariance, and Stability, 2022; oral presentation
  International Conference on Learning Representations (ICLR), 2023; spotlight (notable-top-25%)
  [arXiv, code]
• On Feature Learning in the Presence of Spurious Correlations
  Pavel Izmailov*, Polina Kirichenko*, Nate, Gruver*, Andrew Gordon Wilson
  Neural Information Processing Systems (NeurIPS), 2022
  [arXiv, code]
• Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers
  Wanqian Yang, Polina Kirichenko, Micah Goldblum, Andrew Gordon Wilson
  Neural Information Processing Systems (NeurIPS), 2022
  [arXiv]
• Does Knowledge Distillation Really Work?
  Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A. Alemi, Andrew Gordon Wilson
  Neural Information Processing Systems (NeurIPS), 2021
  [arXiv]
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
  Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu
  ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (spotlight talk), 2021
  [arXiv, poster]
• Why Normalizing Flows Fail to Detect Out-of-Distribution Data
  Polina Kirichenko*, Pavel Izmailov*, Andrew Gordon Wilson
  ICML workshop on Invertible Neural Networks and Normalizing Flows, 2020
  Neural Information Processing Systems (NeurIPS), 2020
  [arXiv, poster]
• Semi-Supervised Learning with Normalizing Flows
  Pavel Izmailov*, Polina Kirichenko*, Marc Finzi*, Andrew Gordon Wilson
  ICML workshop on Invertible Neural Nets and Normalizing Flows, 2019
  14th Women in Machine Learning workshop (co-located with NeurIPS), 2019
  International Conference on Machine Learning (ICML), 2020
  [arXiv, PMLR, code, poster]
• Subspace Inference for Bayesian Deep Learning
  Pavel Izmailov*, Wesley Maddox*, Polina Kirichenko*, Timur Garipov*, Dmitry Vetrov, Andrew Gordon Wilson
  ICML workshop on Uncertainty & Robustness in Deep Learning (contributed talk), 2019
  Uncertainty in Artificial Intelligence (UAI), 2019
  [arXiv, code, UDL poster, UAI poster]
• SWALP: Stochastic Weight Averaging in Low-Precision Training
  Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa
  International Conference on Machine Learning (ICML), 2019
  [arXiv, PMLR, code]

Invited Talks

• Towards Robust and Reliable Deep Learning
  Princeton, Visual AI Lab seminar
  
• Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
  Oral presentation at ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability
  [video]
• Applications of Normalizing Flows: Semi-Supervised Learning, Anomaly Detection, and Continual Learning
  Keynote talk at ICML 2021 Workshop on Representation Learning for Finance and E-Commerce Applications
  [video]
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
  Spotlight talk at INNF+ workshop at ICML 2021
  [video]
• Understanding Semantic Anomaly Detection with Generative Networks
  ML Collective 2021, Deep Learning: Classics and Trends
  [slides]
• Normalizing Flows for Anomaly Detection
  Technical University of Denmark
  [video]
• Anomaly Detection via Generative Models
  Open Data Science DafaFest 2020, Uncertainty in ML Workshop
  [video]
• Why Normalizing Flows Fail to Detect Out-of-Distribution Data
  INNF+ workshop at ICML 2020; NeurIPS 2020
  [ICML video, NeurIPS video]
• How do we build neural networks we can trust?
  Broad Institute of MIT and Harvard
  [video, slides]
• Subspace Inference for Bayesian Deep Learning
  ICML workshop on Uncertainty & Robustness in Deep Learning
  [video, slides]