Feature-based transfer is one of the most effective methodologies for transfer learning. Existing studies usually assume that the learned new feature representation is \emph{domain-invariant}, and thus train a transfer model $\mathcal{M}$ on the source domain. In this paper, we consider a more realistic scenario where the new feature representation is suboptimal and small divergence still exists across domains. We propose a new transfer model called Randomized Transferable Machine (RTM) to handle such small divergence of domains. Specifically, we work on the new source and target data learned from existing feature-based transfer methods. The key idea is to enlarge source training data populations by randomly corrupting the new source data using some noises, and then train a transfer model $\widetilde{\mathcal{M}}$ that performs well on all the corrupted source data populations. In principle, the more corruptions are made, the higher the probability of the new target data can be covered by the constructed source data populations, and thus better transfer performance can be achieved by $\widetilde{\mathcal{M}}$. An ideal case is with infinite corruptions, which however is infeasible in reality. We develop a marginalized solution that enables to train an $\widetilde{\mathcal{M}}$ without conducting any corruption but equivalent to be trained using infinite source noisy data populations. We further propose two instantiations of $\widetilde{\mathcal{M}}$, which theoretically show the transfer superiority over the conventional transfer model $\mathcal{M}$. More importantly, both instantiations have closed-form solutions, leading to a fast and efficient training process. Experiments on various real-world transfer tasks show that RTM is a promising transfer model.
Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement
Department of Computer Science and Engineering, the Hong Kong University of Science and Technology, Hong Kong, China（香港科技大学计算机科学与工程系）；Department of Biomedical Engineering, Case Western Reserve University, OH, USA（凯斯西储大学生物医学工程系）；School of Data Science, Lingnan University, Hong Kong, China（岭南大学数据科学学院）；Department of Chemical and Biological Engineering and Division of Life Science, Hong Kong University of Science and Technology, Hong Kong, China（香港科技大学化学与生物工程系）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Futian, Shenzhen, China（香港科技大学深圳-香港协同创新研究院）；State Key Laboratory of Nervous System Disorders, The Hong Kong University of Science and Technology, Hong Kong, China（香港科技大学神经系统疾病国家重点实验室）
Transferable Graph Condensation from the Causal Perspective
Southwestern University of Finance and Economics（西南财经大学）；Tsinghua University（清华大学）；Ant Group（蚂蚁集团）；Dongbei University of Finance and Economics（东北财经大学）；Emory University（埃默里大学）；Xiangjiang Laboratory（湘江实验室）
Determinantal Point Processes in Randomized Numerical Linear Algebra
University of California, Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Randomized Numerical Linear Algebra（RandNLA）使用随机性来开发用于科学计算、数据科学、机器学习等中出现的矩阵问题的改进算法。行列式点过程（DPPs）是一类随机点过程，其概率分布的特征在于核矩阵的子行列式。最近的工作揭示了DPP和RandNLA之间的深刻而富有成效的联系，这导致了新的保证和改进的算法，这两个领域都感兴趣。我们提供了一个概述这一令人兴奋的新的研究路线，包括简要介绍RandNLA和DPP，以及DPP的经典线性代数任务，如最小二乘回归，低秩近似和Nyström方法的应用。例如，使用DPP的随机抽样导致了最小二乘的新的无偏估计量，使这些算法的统计和推理理解更加精确; DPP在某种意义上是Nyström方法的最佳随机算法;而称为杠杆分数抽样的RandNLA技术可以作为DPP的边际分布而导出。我们还讨论了最近的算法的发展，说明，虽然不是很有效的标准RandNLA技术，基于DPP的算法只是适度更昂贵。
Towards transferable lightweight neuromorphic computing through a model-free temporal-switch framework
State Key Laboratory of Integrated Chips and Systems（集成芯片与系统国家重点实验室）；Research Institute of Intelligent Complex Systems（智能复杂系统研究院）；Frontier Institute of Chip and System（芯片与系统前沿院）；School of Mathematical Sciences and Shanghai Center for Mathematical Sciences（数学科学学院和上海数学中心）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain Science, Institute of Brain Science（医学神经生物学国家重点实验室和教育部脑科学前沿中心，脑科学研究院）
