2024
  1. Hierarchical factor covariance models via multilevel low rank matrices
    Tetiana Parshakova, Trevor Hastie, and Stephen Boyd
    In preparation, 2024
  2. Distributed optimization: Analysis and synthesis via circuits
    Stephen Boyd, Tetiana Parshakova, Ernest Ryu, and Jaewook Suh
    In preparation, 2024
  3. Factor fitting, rank allocation, and partitioning in multilevel low rank matrices
    Tetiana Parshakova, Trevor Hastie, Eric Darve, and Stephen Boyd
    To appear in Optimization, Discrete Mathematics, and Applications to Data Sciences, edited by M. Rassias, A. Nikeghbali, and P. Pardalos, Springer, 2024
    paper Code
2023
  1. Efficient graph field integrators meet point clouds
    Krzysztof Choromanski, Arijit Sehanobish, Han Lin, Yunfan Zhao, Eli Berger, Tetiana Parshakova, and  others
    International Conference on Machine Learning, 2023
    paper Code
  2. Implementation of an oracle-structured bundle method for distributed optimization
    Tetiana Parshakova, Fangzhao Zhang, and Stephen Boyd
    Optimization and Engineering, 2023
    paper Code
2022
  1. Interpolation method and apparatus for arithmetic functions
    William C. Athas, Zaid M. Nadeem, and Tetiana Parshakova
    Mar 2022
    US Patent App. 17/085,971
    website
  2. Methods and systems for producing neural sequential models
    Tetiana Parshakova, Marc Dymetman, and Jean-Marc Andréoli
    Mar 2022
    US Patent App. 17/018,754
    website
2019
  1. Distributional reinforcement learning for energy-based sequential models
    Tetiana Parshakova, Jean-Marc Andreoli, and Marc Dymetman
    NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop, Dec 2019
    paper Code
  2. Global autoregressive models for data-efficient sequence learning
    Tetiana Parshakova, Jean-Marc Andreoli, and Marc Dymetman
    The SIGNLL Conference on Computational Natural Language Learning, Sep 2019
    paper Code
  3. Latent question interpretation through variational adaptation
    Tetiana Parshakova, Francois Rameau, Andriy Serdega, In So Kweon, and Dae-Shik Kim
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, Jul 2019
    paper Code
  4. Latent question interpretation: parameter adaptation using interpretation policy
    Tetiana Parshakova
    Feb 2019
    paper
2018
  1. Latent question interpretation through parameter adaptation using stochastic neuron
    Tetiana Parshakova, and Dae-Shik Kim
    In MRC@ IJCAI, Jul 2018
    paper Code
  2. UMorph: Self-change tracker to reflect yourself to the future and past
    Tetiana Parshakova, and Daniel Saakes
    In Proceedings of the 2018 ACM Conference Companion Publication on Designing Interactive Systems, Jun 2018
    paper
2017
  1. Furniture that learns to move itself
    Tetiana Parshakova, Minjoo Cho, Alvaro Cassinelli, and Daniel Saakes
    In Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems, May 2017
    paper
2016
  1. Ratchair: Furniture learns to move itself with vibration
    Tetiana Parshakova, Minjoo Cho, Alvaro Cassinelli, and Daniel Saakes
    In ACM SIGGRAPH 2016 Emerging Technologies, Jul 2016
    paper