7 papers
On the Local Linear Convergence of Operator Splitting Methods for Conic Programming
Lijun Ding, Haihao Lu, Jinwen Yang
Operator-splitting methods such as the primal-dual hybrid gradient method (PDHG) and the alternating direction method of multipliers (ADMM) often exhibit linear convergence on coni…
TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification
Xinyu Chen, HanQin Cai, Lijun Ding +1
We present TailedTS, a large-scale benchmark dataset derived from Wikipedia hourly page view observations throughout 2024, specifically designed to test time series forecasting mod…
Low-Rank Tensor Estimation from Nonlinear Observations: A Unified Framework
Junren Chen, Lijun Ding, Dong Xia +1
We consider the estimation of a tensor of Tucker rank from the nonlinear observations $\{y_i=f_i(\langle A_i,X^\star\rangle)\}_{…
Interpretable Time Series Autoregression for Periodicity Quantification
Xinyu Chen, Vassilis Digalakis, Lijun Ding +2
Time series autoregression (AR) is a classical tool for modeling auto-correlations and periodic structures in real-world systems. We revisit this model from an interpretable machin…
New Understandings and Computation on Augmented Lagrangian Methods for Low-Rank Semidefinite Programming
Lijun Ding, Haihao Lu, Jinwen Yang
Augmented Lagrangian Method (ALM) combined with Burer-Monteiro (BM) factorization, dubbed ALM-BM, offers a powerful approach for solving large-scale low-rank semidefinite programs…
How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
Nuoya Xiong, Lijun Ding, Simon S. Du
This paper rigorously shows how over-parameterization changes the convergence behaviors of gradient descent (GD) for the matrix sensing problem, where the goal is to recover an unk…
Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
Vasileios Charisopoulos, Yudong Chen, Damek Davis +3
The task of recovering a low-rank matrix from its noisy linear measurements plays a central role in computational science. Smooth formulations of the problem often exhibit an undes…