A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization

Kavli Affiliate: Yi Zhou | First 5 Authors: Ziyi Chen, Bhavya Kailkhura, Yi Zhou, , | Summary: Many important machine learning applications involve regularized nonconvex bi-level optimization. However, the existing gradient-based bi-level optimization algorithms cannot handle nonconvex or nonsmooth regularizers, and they suffer from a high computation complexity in nonconvex bi-level optimization. In this work, […]


Continue.. A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization

A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization

Kavli Affiliate: Yi Zhou | First 5 Authors: Ziyi Chen, Bhavya Kailkhura, Yi Zhou, , | Summary: Many important machine learning applications involve regularized nonconvex bi-level optimization. However, the existing gradient-based bi-level optimization algorithms cannot handle nonconvex or nonsmooth regularizers, and they suffer from a high computation complexity in nonconvex bi-level optimization. In this work, […]


Continue.. A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization

A quantum-inspired tensor network method for constrained combinatorial optimization problems

Kavli Affiliate: Cheng Peng | First 5 Authors: Tianyi Hao, Xuxin Huang, Chunjing Jia, Cheng Peng, | Summary: Combinatorial optimization is of general interest for both theoretical study and real-world applications. Fast-developing quantum algorithms provide a different perspective on solving combinatorial optimization problems. In this paper, we propose a quantum inspired algorithm for general locally […]


Continue.. A quantum-inspired tensor network method for constrained combinatorial optimization problems

A quantum-inspired tensor network method for constrained combinatorial optimization problems

Kavli Affiliate: Cheng Peng | First 5 Authors: Tianyi Hao, Xuxin Huang, Chunjing Jia, Cheng Peng, | Summary: Combinatorial optimization is of general interest for both theoretical study and real-world applications. Fast-developing quantum algorithms provide a different perspective on solving combinatorial optimization problems. In this paper, we propose a quantum-inspired tensor-network-based algorithm for general locally […]


Continue.. A quantum-inspired tensor network method for constrained combinatorial optimization problems

Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing

Kavli Affiliate: Zheng Zhu | First 5 Authors: Qingping Zheng, Jiankang Deng, Zheng Zhu, Ying Li, Stefanos Zafeiriou | Summary: This paper probes intrinsic factors behind typical failure cases (e.g. spatial inconsistency and boundary confusion) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning […]


Continue.. Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing

Delving into the Estimation Shift of Batch Normalization in a Network

Kavli Affiliate: Yi Zhou | First 5 Authors: Lei Huang, Yi Zhou, Tian Wang, Jie Luo, Xianglong Liu | Summary: Batch normalization (BN) is a milestone technique in deep learning. It normalizes the activation using mini-batch statistics during training but the estimated population statistics during inference. This paper focuses on investigating the estimation of population […]


Continue.. Delving into the Estimation Shift of Batch Normalization in a Network

Sense Embeddings are also Biased–Evaluating Social Biases in Static and Contextualised Sense Embeddings

Kavli Affiliate: Yi Zhou | First 5 Authors: Yi Zhou, Masahiro Kaneko, Danushka Bollegala, , | Summary: Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior work […]


Continue.. Sense Embeddings are also Biased–Evaluating Social Biases in Static and Contextualised Sense Embeddings

Possible chiral spin liquid state in the $S=1/2$ kagome Heisenberg model

Kavli Affiliate: Yi Zhou | First 5 Authors: Rong-Yang Sun, Hui-Ke Jin, Hong-Hao Tu, Yi Zhou, | Summary: The nature of the ground state for the $S = 1/2$ kagome Heisenberg antiferromagnet (KHAF) has been elusive. We revisit this challenging problem and provide numerical evidence that its ground state might be a chiral spin liquid. […]


Continue.. Possible chiral spin liquid state in the $S=1/2$ kagome Heisenberg model

GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework

Kavli Affiliate: Zheng Zhu | First 5 Authors: Ming Wang, Beibei Lin, Xianda Guo, Lincheng Li, Zheng Zhu | Summary: Many gait recognition methods first partition the human gait into N-parts and then combine them to establish part-based feature representations. Their gait recognition performance is often affected by partitioning strategies, which are empirically chosen in […]


Continue.. GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework

Towards performant and reliable undersampled MR reconstruction via diffusion model sampling

Kavli Affiliate: Cheng Peng | First 5 Authors: Cheng Peng, Pengfei Guo, S. Kevin Zhou, Vishal Patel, Rama Chellappa | Summary: Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time. To this end, current State-of-The-Art (SoTA) approaches leverage deep neural networks and supervised training to learn a recovery model. While these approaches […]


Continue.. Towards performant and reliable undersampled MR reconstruction via diffusion model sampling