Finding Local Minimax Points via (Stochastic) Cubic-Regularized GDA: Global Convergence and Complexity

Kavli Affiliate: Yi Zhou | First 5 Authors: Ziyi Chen, Qunwei Li, Yi Zhou, , | Summary: Standard gradient descent-ascent (GDA)-type algorithms can only find stationary points in nonconvex minimax optimization, which are far more sub-optimal than local minimax points. In this work, we develop GDA-type algorithms that globally converge to local minimax points in […]


Continue.. Finding Local Minimax Points via (Stochastic) Cubic-Regularized GDA: Global Convergence and Complexity

Assisted Learning for Organizations with Limited Data

Kavli Affiliate: Yi Zhou | First 5 Authors: Cheng Chen, Jiaying Zhou, Jie Ding, Yi Zhou, | Summary: We develop an assisted learning framework for assisting organization-level learners to improve their learning performance with limited and imbalanced data. In particular, learners at the organization level usually have sufficient computation resource, but are subject to stringent […]


Continue.. Assisted Learning for Organizations with Limited Data

Assisted Learning for Organizations with Limited Imbalanced Data

Kavli Affiliate: Yi Zhou | First 5 Authors: Cheng Chen, Jiaying Zhou, Jie Ding, Yi Zhou, | Summary: In the era of big data, many big organizations are integrating machine learning into their work pipelines to facilitate data analysis. However, the performance of their trained models is often restricted by limited and imbalanced data available […]


Continue.. Assisted Learning for Organizations with Limited Imbalanced Data

Subregion Spectrum Form Factor via Pseudo Entropy

Kavli Affiliate: Masahiro Nozaki | First 5 Authors: Kanato Goto, Masahiro Nozaki, Kotaro Tamaoka, , | Summary: We introduce a subsystem generalization of the spectral form factor via pseudo entropy, the von-Neumann entropy for the reduced transition matrix. We consider a transition matrix between the thermofield double state and its time-evolved state in two-dimensional conformal […]


Continue.. Subregion Spectrum Form Factor via Pseudo Entropy

Unveiling a critical stripy state in the triangular-lattice SU(4) spin-orbital model

Kavli Affiliate: Yi Zhou | First 5 Authors: Hui-Ke Jin, Rong-Yang Sun, Hong-Hao Tu, Yi Zhou, | Summary: The simplest spin-orbital model can host a nematic spin-orbital liquid state on the triangular lattice. We provide clear evidence that the ground state of the SU(4) Kugel-Khomskii model on the triangular lattice can be well described by […]


Continue.. Unveiling a critical stripy state in the triangular-lattice SU(4) spin-orbital model

A likelihood based sensitivity analysis for publication bias on summary ROC in meta-analysis of diagnostic test accuracy

Kavli Affiliate: Yi Zhou | First 5 Authors: Yi Zhou, Ao Huang, Satoshi Hattori, , | Summary: In meta-analysis of diagnostic test accuracy, summary receiver operating characteristic (SROC) is a recommended method to summarize the discriminant capacity of a diagnostic test in the presence of study-specific cutoff values and the area under the SROC (SAUC) […]


Continue.. A likelihood based sensitivity analysis for publication bias on summary ROC in meta-analysis of diagnostic test accuracy

Enhanced spin-orbit coupling and orbital moment in ferromagnets by electron correlations

Kavli Affiliate: Bo Gu | First 5 Authors: Ze Liu, Jing-Yang You, Bo Gu, Sadamichi Maekawa, Gang Su | Summary: In atomic physics, the Hund rule says that the largest spin and orbital state is realized due to the interplay of the spin-orbit coupling (SOC) and the Coulomb interactions. Here, we show that in ferromagnetic […]


Continue.. Enhanced spin-orbit coupling and orbital moment in ferromagnets by electron correlations

An Efficient Training Approach for Very Large Scale Face Recognition

Kavli Affiliate: Zheng Zhu | First 5 Authors: Kai Wang, Shuo Wang, Panpan Zhang, Zhipeng Zhou, Zheng Zhu | Summary: Face recognition has achieved significant progress in deep learning era due to the ultra-large-scale and welllabeled datasets. However, training on the outsize datasets is time-consuming and takes up a lot of hardware resource. Therefore, designing […]


Continue.. An Efficient Training Approach for Very Large Scale Face Recognition

XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

Kavli Affiliate: Cheng Peng | First 5 Authors: Cheng Peng, Haofu Liao, Gina Wong, Jiebo Luo, Shaohua Kevin Zhou | Summary: A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane. Hence, radiograph analysis naturally requires physicians to relate the prior about 3D […]


Continue.. XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors