Timezone: »
Poster
Effective Meta-Regularization by Kernelized Proximal Regularization
Weisen Jiang · James Kwok · Yu Zhang
We study the problem of meta-learning, which has proved to be advantageous to accelerate learning new tasks with a few samples. The recent approaches based on deep kernels achieve the state-of-the-art performance. However, the regularizers in their base learners are not learnable. In this paper, we propose an algorithm called MetaProx to learn a proximal regularizer for the base learner. We theoretically establish the convergence of MetaProx. Experimental results confirm the advantage of the proposed algorithm.
Author Information
Weisen Jiang (HKUST)
James Kwok (Hong Kong University of Science and Technology)
Yu Zhang (HKUST)
More from the Same Authors
-
2021 Spotlight: TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation »
Haoang Chi · Feng Liu · Wenjing Yang · Long Lan · Tongliang Liu · Bo Han · William Cheung · James Kwok -
2023 Poster: Efficient Hyper-parameter Optimization with Cubic Regularization »
Zhenqian Shen · Hansi Yang · Yong Li · James Kwok · Quanming Yao -
2023 Poster: Nonparametric Teaching for Multiple Learners »
Chen Zhang · Xiaofeng Cao · Weiyang Liu · Ivor Tsang · James Kwok -
2022 Poster: Multi-Objective Deep Learning with Adaptive Reference Vectors »
Weiyu Chen · James Kwok -
2022 Poster: Dynamic Sparse Network for Time Series Classification: Learning What to “See” »
Qiao Xiao · Boqian Wu · Yu Zhang · Shiwei Liu · Mykola Pechenizkiy · Elena Mocanu · Decebal Constantin Mocanu -
2021 Poster: TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation »
Haoang Chi · Feng Liu · Wenjing Yang · Long Lan · Tongliang Liu · Bo Han · William Cheung · James Kwok -
2021 Poster: Multi-Objective Meta Learning »
Feiyang YE · Baijiong Lin · Zhixiong Yue · Pengxin Guo · Qiao Xiao · Yu Zhang -
2020 Poster: Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network »
Lifeng Shen · Zhuocong Li · James Kwok -
2020 Poster: Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS »
Han Shi · Renjie Pi · Hang Xu · Zhenguo Li · James Kwok · Tong Zhang -
2019 Poster: Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback »
Shuai Zheng · Ziyue Huang · James Kwok -
2019 Poster: Normalization Helps Training of Quantized LSTM »
Lu Hou · Jinhua Zhu · James Kwok · Fei Gao · Tao Qin · Tie-Yan Liu -
2018 Poster: Learning to Multitask »
Yu Zhang · Ying Wei · Qiang Yang -
2018 Poster: Scalable Robust Matrix Factorization with Nonconvex Loss »
Quanming Yao · James Kwok -
2015 Poster: Fast Second Order Stochastic Backpropagation for Variational Inference »
Kai Fan · Ziteng Wang · Jeff Beck · James Kwok · Katherine Heller -
2012 Poster: Mandatory Leaf Node Prediction in Hierarchical Multilabel Classification »
Wei Bi · James Kwok -
2009 Poster: Accelerated Gradient Methods for Stochastic Optimization and Online Learning »
Chonghai Hu · James Kwok · Weike Pan