no code implementations • 22 Dec 2023 • Junyu Chen, Binh T. Nguyen, Yong Sheng Soh
The Gromov-Wasserstein (GW) distance is a variant of the optimal transport problem that allows one to match objects between incomparable spaces.
no code implementations • 31 May 2023 • Subhroshekhar Ghosh, Aaron Y. R. Low, Yong Sheng Soh, Zhuohang Feng, Brendan K. Y. Tan
We apply our paradigm to investigate the dictionary learning problem for the groups SO(2) and SO(3).
no code implementations • 27 Dec 2022 • Oscar Leong, Eliza O'Reilly, Yong Sheng Soh, Venkat Chandrasekaran
In this paper, we seek a systematic understanding of the power and the limitations of convex regularization by investigating the following questions: Given a distribution, what is the optimal regularizer for data drawn from the distribution?
no code implementations • 29 Sep 2021 • Aaron Yi Rui Low, Subhroshekhar Ghosh, Yong Sheng Soh
Thus, a naturally significant class of functions consists of those that are intrinsic to the problem, in the sense of being independent of such base change or relabelling; in other words invariant under the conjugation action by a group.
no code implementations • 2 Aug 2021 • Yong Sheng Soh, Antonios Varvitsiotis
Given a matrix $X\in \mathbb{R}^{m\times n}_+$ with non-negative entries, the cone factorization problem over a cone $\mathcal{K}\subseteq \mathbb{R}^k$ concerns computing $\{ a_1,\ldots, a_{m} \} \subseteq \mathcal{K}$ and $\{ b_1,\ldots, b_{n} \} \subseteq~\mathcal{K}^*$ belonging to its dual so that $X_{ij} = \langle a_i, b_j \rangle$ for all $i\in [m], j\in [n]$.
no code implementations • NeurIPS 2021 • Yong Sheng Soh, Antonios Varvitsiotis
The most widely used algorithm for computing NMFs of a matrix is the Multiplicative Update algorithm developed by Lee and Seung, in which nonnegativity of the updates is preserved by scaling with positive diagonal matrices.
no code implementations • 15 Jul 2020 • Yong Sheng Soh
The dictionary learning problem concerns the task of representing data as sparse linear sums drawn from a smaller collection of basic building blocks.
no code implementations • 12 Feb 2020 • Chi Zhang, Yong Sheng Soh, Ling Feng, Tianyi Zhou, Qianxiao Li
While current machine learning models have impressive performance over a wide range of applications, their large size and complexity render them unsuitable for tasks such as remote monitoring on edge devices with limited storage and computational power.
no code implementations • 6 Nov 2019 • Utkan Candogan, Yong Sheng Soh, Venkat Chandrasekaran
The affine inverse eigenvalue problem consists of identifying a real symmetric matrix with a prescribed set of eigenvalues in an affine space.
Optimization and Control 15A18, 15A29, 90C22
no code implementations • 11 Mar 2019 • Yong Sheng Soh, Venkat Chandrasekaran
Our numerical experiments highlight the utility of our framework over previous approaches in settings in which the measurements available are noisy or small in number as well as those in which the underlying set to be reconstructed is non-polyhedral.
Statistics Theory Computational Geometry Optimization and Control Statistics Theory
no code implementations • 5 Jan 2017 • Yong Sheng Soh, Venkat Chandrasekaran
The regularizers obtained using our framework can be employed effectively in semidefinite programming relaxations for solving inverse problems.
no code implementations • 11 Dec 2014 • Yong Sheng Soh, Venkat Chandrasekaran
We consider change-point estimation in a sequence of high-dimensional signals given noisy observations.
Statistics Theory Information Theory Information Theory Optimization and Control Statistics Theory