Existing MAP inference algorithms for determinantal point processes (DPPs) need to calculate determinants or conduct eigenvalue decomposition generally at the scale of the full kernel, which presents a great challenge for real-world applications. In this paper, we introduce a class of DPPs, called BwDPPs, that are characterized by an almost block diagonal kernel matrix and thus can allow efficient block-wise MAP inference. Furthermore, BwDPPs are successfully applied to address the difficulty of selecting change-points in the problem of change-point detection (CPD), which results in a new BwDPP-based CPD method, named BwDppCpd. In BwDppCpd, a preliminary set of change-point candidates is first created based on existing well-studied metrics. Then, these change-point candidates are treated as DPP items, and DPP-based subset selection is conducted to give the final estimate of the change-points that favours both quality and diversity. The effectiveness of BwDppCpd is demonstrated through extensive experiments on five real-world datasets.
Waseda University（早稻田大学）；The National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）
In this study, a perceptually hidden object-recognition method is investigated to generate secure images recognizable by humans but not machines. Hence, both the perceptual information hiding and the corresponding object recognition methods should be developed. Block-wise image scrambling is introduced to hide perceptual information from a third party. In addition, an adaptation network is proposed to recognize those scrambled images. Experimental comparisons conducted using CIFAR datasets demonstrated that the proposed adaptation network performed well in incorporating simple perceptual infor…
Finetuning can be used to tackle domain-specific tasks by transferring knowledge. Previous studies on finetuning focused on adapting only the weights of a task-specific classifier or re-optimizing all layers of the pre-trained model using the new task data. The first type of methods cannot mitigate the mismatch between a pre-trained model and the new task data, and the second type of methods easily cause over-fitting when processing tasks with limited data. To explore the effectiveness of fine-tuning, we propose a novel block-wise optimization mechanism, which adapts the weights of a group of …
This paper deals with the asymptotic distribution of Wishart matrix and its application to the estimation of the population matrix parameter when the population eigenvalues are block-wise infinitely dispersed. We show that the appropriately normalized eigenvectors and eigenvalues asymptotically generate two Wishart matrices and one normally distributed random matrix, which are mutually independent. For a family of orthogonally equivariant estimators, we calculate the asymptotic risks with respect to the entropy or the quadratic loss function and derive the asymptotically best estimator among t…
The stochastic block model is widely used for detecting community structures in network data. How to test the goodness-of-fit of the model is one of the fundamental problems and has gained growing interests in recent years. In this article, we propose a novel goodness-of-fit test based on the maximum entry of the centered and re-scaled adjacency matrix for the stochastic block model. One noticeable advantage of the proposed test is that the number of communities can be allowed to grow linearly with the number of nodes ignoring a logarithmic factor. We prove that the null distribution of the te…
It is well known that the empirical likelihood ratio confidence region suffers finite sample under-coverage issue, and this severely hampers its application in statistical inferences.} The root cause of this under-coverage is an upper limit imposed by the convex hull of the estimating functions that is used in the construction of the profile empirical likelihood. For i.i.d data, various methods have been proposed to solve this issue by modifying the convex hull, but it is not clear how well these methods perform when the data are no longer independent. In this paper, we propose an adjusted blo…
ETH Zurich（苏黎世联邦理工学院）；University of California, Berkeley（加州大学伯克利分校）
We analyze the convergence rate of the randomized Newton-like method introduced by Qu et. al. (2016) for smooth and convex objectives, which uses random coordinate blocks of a Hessian-over-approximation matrix $\bM$ instead of the true Hessian. The convergence analysis of the algorithm is challenging because of its complex dependence on the structure of $\bM$. However, we show that when the coordinate blocks are sampled with probability proportional to their determinant, the convergence rate depends solely on the eigenvalue distribution of matrix $\bM$, and has an analytically tractable form. …
Massachusetts Institute of Technology（麻省理工学院）；Google Brain（谷歌大脑）
Determinantal Point Processes (DPPs) provide an elegant and versatile way to sample sets of items that balance the point-wise quality with the set-wise diversity of selected items. For this reason, they have gained prominence in many machine learning applications that rely on subset selection. However, sampling from a DPP over a ground set of size $N$ is a costly operation, requiring in general an $O(N^3)$ preprocessing cost and an $O(Nk^3)$ sampling cost for subsets of size $k$. We approach this problem by introducing DPPNets: generative deep models that produce DPP-like samples for arbitrary…
Markov basis for statistical model of contingency tables gives a useful tool for performing the conditional test of the model via Markov chain Monte Carlo method. In this paper we derive explicit forms of Markov bases for change point models and block diagonal effect models, which are typical block-wise effect models of two-way contingency tables, and perform conditional tests with some real data sets.
Huber's criterion can be used for robust joint estimation of regression and scale parameters in the linear model. Huber's (Huber, 1981) motivation for introducing the criterion stemmed from non-convexity of the joint maximum likelihood objective function as well as non-robustness (unbounded influence function) of the associated ML-estimate of scale. In this paper, we illustrate how the original algorithm proposed by Huber can be set within the block-wise minimization majorization framework. In addition, we propose novel data-adaptive step sizes for both the location and scale, which are furthe…
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Knowledge distillation (KD) is a popular method for reducing the computational overhead of deep network inference, in which the output of a teacher model is used to train a smaller, faster student model. Hint training (i.e., FitNets) extends KD by regressing a student model's intermediate representation to a teacher model's intermediate representation. In this work, we introduce bLock-wise Intermediate representation Training (LIT), a novel model compression technique that extends the use of intermediate representations in deep network compression, outperforming KD and hint training. LIT has t…
Extreme multi-label classification aims to learn a classifier that annotates an instance with a relevant subset of labels from an extremely large label set. Many existing solutions embed the label matrix to a low-dimensional linear subspace, or examine the relevance of a test instance to every label via a linear scan. In practice, however, those approaches can be computationally exorbitant. To alleviate this drawback, we propose a Block-wise Partitioning (BP) pretreatment that divides all instances into disjoint clusters, to each of which the most frequently tagged label subset is attached. On…
Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a way to reduce the memory and computation footprint of these models has seen significant research attention in recent years. In this paper, we present a new method for \emph{dynamic sparseness}, whereby part of the computations are omitted dynamically, based on the input. For efficiency, we combined the idea of dynamic sparseness with block-wise matrix-vector multiplications. In contrast to static sparseness, which pe…
University of California, Davis（加利福尼亚大学戴维斯分校）；Harvard T.H. Chan School of Public Health（哈佛陈曾熙公共卫生学院）
Matrix completion has attracted attention in many fields, including statistics, applied mathematics, and electrical engineering. Most of the works focus on the independent sampling models under which the observed entries are sampled independently. Motivated by applications in the integration of knowledge graphs derived from multi-source biomedical data such as those from Electronic Health Records (EHR) and biomedical text, we propose the {\bf B}lock-wise {\bf O}verlapping {\bf N}oisy {\bf M}atrix {\bf I}ntegration (BONMI) to treat blockwise missingness of symmetric matrices representing relate…
Data quantization is an effective method to accelerate neural network training and reduce power consumption. However, it is challenging to perform low-bit quantized training: the conventional equal-precision quantization will lead to either high accuracy loss or limited bit-width reduction, while existing mixed-precision methods offer high compression potential but failed to perform accurate and efficient bit-width assignment. In this work, we propose DYNASTY, a block-wise dynamic-precision neural network training framework. DYNASTY provides accurate data sensitivity information through fast o…
University of Chinese Academy of Sciences（中国科学院大学）；Sensetime Research Institute（商汤研究院）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained to choose component layers sequentially. We stack the block to construct the whole auto-generated network. To acceler…
University of Chinese Academy of Sciences（中国科学院大学）；SenseTime Research（商汤科技研究院）；CAS Center for Excellence of Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained sequentially to choose component layers. We stack the block to construct the whole auto-generated network. To acceler…
Department of Electrical and Computer Engineering, University of Alberta（阿尔伯塔大学电气与计算机工程系）；School of Computer Science, Wuhan University（武汉大学计算机学院）
Many machine learning models, including those with non-smooth regularizers, can be formulated as consensus optimization problems, which can be solved by the alternating direction method of multipliers (ADMM). Many recent efforts have been made to develop asynchronous distributed ADMM to handle large amounts of training data. However, all existing asynchronous distributed ADMM methods are based on full model updates and require locking all global model parameters to handle concurrency, which essentially serializes the updates from different workers. In this paper, we present a novel block-wise,…
Facebook AI Research（脸书人工智能研究院）；University of Washington（华盛顿大学）
Stateful optimizers maintain gradient statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can be used to accelerate optimization compared to plain stochastic gradient descent but uses memory that might otherwise be allocated to model parameters, thereby limiting the maximum size of models trained in practice. In this paper, we develop the first optimizers that use 8-bit statistics while maintaining the performance levels of using 32-bit optimizer states. To overcome the resulting computational, quantization, a…
Efficient ANN-Guided Distillation: Aligning Rate-based Features of Spiking Neural Networks through Hybrid Block-wise Replacement
ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC联合学院）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）
Since production-level trained deep neural networks (DNNs) are of a great business value, protecting such DNN models against copyright infringement and unauthorized access is in a rising demand. However, conventional model protection methods focused only the image classification task, and these protection methods were never applied to semantic segmentation although it has an increasing number of applications. In this paper, we propose to protect semantic segmentation models from unauthorized access by utilizing block-wise transformation with a secret key for the first time. Protected models ar…
University of California, Davis（加州大学戴维斯分校）；Google Research（谷歌研究院）
Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing input tokens and a softmax layer for generating output tokens. For problems with a very large vocabulary size, the embedding and the softmax matrices can account for more than half of the model size. For instance, the bigLSTM model achieves state-of- the-art performance on the One-B…
DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data
School of Computer Science and Technology, Shandong University, Qingdao China（山东大学计算机科学与技术学院，青岛中国）；School of Mathematical Science, Peking University, China（北京大学数学科学学院，中国）；IEIT SYSTEM, China（IEIT SYSTEM，中国）；School of Computer Science and Artificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China（上海财经大学计算机科学与人工智能学院，上海中国）；College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院，新加坡）
Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Data
School of Statistics and Data Science, Shanghai University of Finance and Economics（上海财经大学统计与数据科学学院）；Department of Statistics and Data Science, Carnegie Mellon University（卡内基梅隆大学统计与数据科学系）；Department of Statistics, University of California, Irvine（加州大学 Irvine 分校统计系）
Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Department of Data Science, City University of Hong Kong（香港城市大学数据科学系）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Alma Mater Studiorum Università di Bologna（博洛尼亚大学）
In this paper we deal with a network of computing agents with local processing and neighboring communication capabilities that aim at solving (without any central unit) a submodular optimization problem. The cost function is the sum of many local submodular functions and each agent in the network has access to one function in the sum only. In this \emph{distributed} set-up, in order to preserve their own privacy, agents communicate with neighbors but do not share their local cost functions. We propose a distributed algorithm in which agents resort to the Lovàsz extension of their local submodu…
