Search Results for author: Liangzu Peng

Found 12 papers, 7 papers with code

ICL-TSVD: Bridging Theory and Practice in Continual Learning with Pre-trained Models

no code implementations1 Oct 2024 Liangzu Peng, Juan Elenter, Joshua Agterberg, Alejandro Ribeiro, René Vidal

This results in a stable continual learning method with strong empirical performance and theoretical guarantees.

Continual Learning

Efficient and Robust Point Cloud Registration via Heuristics-guided Parameter Search

1 code implementation9 Apr 2024 Tianyu Huang, Haoang Li, Liangzu Peng, Yinlong Liu, Yun-hui Liu

Our strategy largely reduces the search space and can guarantee accuracy with only a few inlier samples, therefore enjoying an excellent trade-off between efficiency and robustness.

Point Cloud Registration

Scalable 3D Registration via Truncated Entry-wise Absolute Residuals

1 code implementation CVPR 2024 Tianyu Huang, Liangzu Peng, René Vidal, Yun-hui Liu

Given an input set of $3$D point pairs, the goal of outlier-robust $3$D registration is to compute some rotation and translation that align as many point pairs as possible.

The Ideal Continual Learner: An Agent That Never Forgets

1 code implementation29 Apr 2023 Liangzu Peng, Paris V. Giampouras, René Vidal

We show that ICL unifies multiple well-established continual learning methods and gives new theoretical insights into the strengths and weaknesses of these methods.

Continual Learning Generalization Bounds

Accelerating Globally Optimal Consensus Maximization in Geometric Vision

no code implementations11 Apr 2023 Xinyue Zhang, Liangzu Peng, Wanting Xu, Laurent Kneip

Branch-and-bound-based consensus maximization stands out due to its important ability of retrieving the globally optimal solution to outlier-affected geometric problems.

Camera Pose Estimation Pose Estimation

On the Convergence of IRLS and Its Variants in Outlier-Robust Estimation

1 code implementation CVPR 2023 Liangzu Peng, Christian Kümmerle, René Vidal

Outlier-robust estimation involves estimating some parameters (e. g., 3D rotations) from data samples in the presence of outliers, and is typically formulated as a non-convex and non-smooth problem.

Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search

no code implementations18 Jul 2022 Liangzu Peng, Mahyar Fazlyab, René Vidal

To induce robustness against outliers for rotation search, prior work considers truncated least-squares (TLS), which is a non-convex optimization problem, and its semidefinite relaxation (SDR) as a tractable alternative.

ARCS: Accurate Rotation and Correspondence Search

1 code implementation CVPR 2022 Liangzu Peng, Manolis C. Tsakiris, René Vidal

We first propose a solver, $\texttt{ARCS}$, that i) assumes noiseless point sets in general position, ii) requires only $2$ inliers, iii) uses $O(m\log m)$ time and $O(m)$ space, and iv) can successfully solve the problem even with, e. g., $m, n\approx 10^6$ in about $0. 1$ seconds.

Unlabeled Principal Component Analysis and Matrix Completion

1 code implementation NeurIPS 2021 Yunzhen Yao, Liangzu Peng, Manolis C. Tsakiris

Allowing for missing entries on top of permutations in UPCA leads to the problem of unlabeled matrix completion, for which we derive theory and algorithms of similar flavor.

Matrix Completion

Homomorphic Sensing of Subspace Arrangements

no code implementations9 Jun 2020 Liangzu Peng, Manolis C. Tsakiris

In this paper, we provide tighter and simpler conditions that guarantee the unique recovery for the single-subspace case, extend the result to the case of a subspace arrangement, and show that the unique recovery in a single subspace is locally stable under noise.

Missing Values Retrieval

Linear Regression without Correspondences via Concave Minimization

1 code implementation17 Mar 2020 Liangzu Peng, Manolis C. Tsakiris

Linear regression without correspondences concerns the recovery of a signal in the linear regression setting, where the correspondences between the observations and the linear functionals are unknown.

regression

An algebraic-geometric approach for linear regression without correspondences

no code implementations12 Oct 2018 Manolis C. Tsakiris, Liangzu Peng, Aldo Conca, Laurent Kneip, Yuanming Shi, Hayoung Choi

This naturally leads to a polynomial system of $n$ equations in $n$ unknowns, which contains $\xi^*$ in its root locus.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.