Consistent Robust Regression
By Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar. 2017
105 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Ilias Diakonikolas
- Dong Yin
- Tian Li
- Jerry Zheng Li
- Sai Praneeth Karimireddy
- Jacob Steinhardt
- Zeyuan Allen-Zhu
- Cong Xie
Citations in the corpus
- Byzantine Stochastic Gradient Descent (2018, background): “Optimization and learning in the presence of adversarial noise is a well-studied problem [4, 5, 15, 20, 22, 28].”
- Sever: A Robust Meta-Algorithm for Stochastic Optimization (2018, background): “A number of papers [NTN11, NT13, BJK15, BJKK17] have proposed efficient algorithms for a type of robust linear regression.”
- Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning (2018, background): “[9] Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, and Purushottam Kar.”
- Choosing the Sample with Lowest Loss makes SGD Robust (2020, background): “Recently, [5, 6, 32, 20, 18] have proposed robust learning algorithms for linear regression which require the computation of gradient over the entire dataset which may be computationally intractable for large datasets.”
- Efficient Algorithms and Lower Bounds for Robust Linear Regression (2018, methodology): “In the context of the estimation task studied in this paper, [BJK15, BJKK17] have proposed efficient algorithms for “robust” linear regression.”
- Tilted Empirical Risk Minimization (2020, background): “In terms of runtime, solving TERM is roughly as efficient as ERM, while CRR tends to run slowly as it scales cubicly with the number of dimensions [6].”
- Efficient Algorithms for Outlier-Robust Regression (2018, background): “It is common for “robust regression” to refer to a scenario where only the labels are allowed to be corrupted adversarially (for example, see [BJKK17] and the references therein), or where the noise obeys some special structure (e.g., [HS10]) (although there are some contexts where both the…”
- Non-convex Optimization for Machine Learning (2017, methodology): “The work of [Bhatia et al., 2017] uses this alternate formulation to arrive at a solution that enjoys consistency properties.”