Sifan Liu

Conference Springer Proceedings in Physics · January 1, 2026 As the basis of shielding design, the shielding calculation program and shielding database need to be verified, validated and improved by using the data from shielding benchmark experiments. Therefore, it's of great significance to carry out deep penetrati ... Full text Cite

Langevin Quasi-Monte Carlo

Conference Advances in Neural Information Processing Systems · January 1, 2023 Langevin Monte Carlo (LMC) and its stochastic gradient versions are powerful algorithms for sampling from complex high-dimensional distributions. To sample from a distribution with density π(θ) ∝ exp(−U(θ)), LMC iteratively generates the next sample by tak ... Cite

RIDGE REGRESSION: STRUCTURE, CROSS-VALIDATION, AND SKETCHING

Conference 8th International Conference on Learning Representations Iclr 2020 · January 1, 2020 We study the following three fundamental problems about ridge regression: (1) what is the structure of the estimator? (2) how to correctly use cross-validation to choose the regularization parameter? and (3) how to accelerate computation without losing too ... Cite

Optimal iterative sketching with the subsampled randomized hadamard transform

Conference Advances in Neural Information Processing Systems · January 1, 2020 Random projections or sketching are widely used in many algorithmic and learning contexts. Here we study the performance of iterative Hessian sketch for least-squares problems. By leveraging and extending recent results from random matrix theory on the lim ... Cite

Asymptotics for sketching in least squares

Conference Advances in Neural Information Processing Systems · January 1, 2019 We consider a least squares regression problem where the data has been generated from a linear model, and we are interested to learn the unknown regression parameters. We consider "sketch-and-solve" methods that randomly project the data first, and do regr ... Cite