Publications
Publications by categories in reverse chronological order.
Preprints
High-dimensional sequential change detection
Robert Malinas, Dogyoon Song, Benjamin D. Robinson and Alfred O. Hero
arXiv preprint (v1, February 2025)Algebraic and statistical properties of the ordinary least squares interpolator
Dennis Shen, Dogyoon Song, Peng Ding and Jasjeet Sekhon arXiv preprint (v2, May 2024)Community detection in high-dimensional graph ensembles
Robert Malinas, Dogyoon Song, Alfred O. Hero
arXiv preprint (v1, December 2023); presented at the Asilomar Conference 2023On separability of covariance in multiway data analysis
Dogyoon Song and Alfred O. Hero
arXiv preprint (v2, October 2023)Deconvolution with unknown error distribution interpreted as blind isotonic regression
Devavrat Shah and Dogyoon Song
arXiv preprint (v3, April 2020); presented at the Allerton Conference 2018Learning RUMs: Reducing mixture to single component via PCA
Devavrat Shah and Dogyoon Song
arXiv preprint (v3, March 2020)
Journal Articles
Local minima structures in Gaussian mixture models
Yudong Chen, Dogyoon Song, Xumei Xi and Yuqian Zhang
IEEE Transactions on Information Theory, 2024On approximations of the PSD cone by a polynomial number of smaller-sized PSD cones
Dogyoon Song and Pablo A. Parrilo
Mathematical Programming, 2023Kronecker-structured covariance models for multiway data
Yu Wang, Zeyu Sun, Dogyoon Song and Alfred O. Hero
Statistics Surveys, 2022On robustness of principal component regression
Anish Agarwal, Devavrat Shah, Dennis Shen and Dogyoon Song
Journal of the American Statistical Association (JASA), 2021; Preliminary version presented at NeurIPS 2019Nearest neighbors for matrix estimation interpreted as blind regression for latent variable model
Yihua Li, Devavrat Shah, Dogyoon Song and Christina Lee Yu
IEEE Transactions on Information Theory, 2019; Preliminary version presented at NeurIPS 2016
Conference Proceedings
Improving training efficiency of diffusion models via multi-stage framework and tailored multi-decoder architecture
Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song and Qing Qu
CVPR 2024Efficient low-dimensional compression of overparameterized models
Soo Min Kwon, Zekai Zhang, Dogyoon Song, Laura Balzano and Qing Qu
AISTATS 2024Errors-in-variables Fréchet regression with low-rank covariate approximation
Dogyoon Song and Kyunghee Han
NeurIPS 2023Minimum-risk recalibration of classifiers
Zeyu Sun, Dogyoon Song and Alfred O. Hero
NeurIPS 2023 (spotlight)Robustness-preserving lifelong learning via dataset condensation
Jinghan Jia, Yihua Zhang, Dogyoon Song, Sijia Liu and Alfred O. Hero
ICASSP 2023Sample-efficient reinforcement learning via low-rank matrix estimation
Devavrat Shah, Dogyoon Song, Zhi Xu and Yuzhe Yang
NeurIPS 2020On robustness of principal component regression
Anish Agarwal, Devavrat Shah, Dennis Shen and Dogyoon Song
NeurIPS 2019 (oral)Blind regression: Nonparametric regression for latent variable models via collaborative filtering
Christina Lee, Yihua Li, Devavrat Shah and Dogyoon Song
NeurIPS 2016Verifying start-up failures in coupled ring oscillators in presence of variability using predictive global optimization
Taehwan Kim, Dogyoon Song, Sangho Youn, Jaejin Park, Hojin Park and Jaeha Kim
IEEE/ACM ICCAD 2013Discretization and discrimination methods for design, verification, and testing of analog/mixed-signal circuits
Jaeha Kim, Jiho Lee, Dogyoon Song, Taehwan Kim, Kyunghoon Kim, Seobin Jung and Sangho Youn
IEEE CICC 2013A low-power high-radix switch fabric based on low-swing signaling and partially-activated input lines
Dogyoon Song and Jaeha Kim
VLSI-DAT 2013
Ph.D. Thesis
- Addressing missing data and scalable optimization for data-driven decision making
Ph.D. Thesis, Massachusetts Institute of Technology, June 2021
Advised by Pablo A. Parrilo and Devavrat Shah
