Searcharxiv⌕ Search

arXiv subjects

Yuan Zhou

Publications and source records attributed to Yuan Zhou.

At least 271 records · Page 15Linked to original sources
arXiv2019

Facets, weak facets, and extreme functions of the Gomory-Johnson infinite group problem

We investigate three competing notions that generalize the notion of a facet of finite-dimensional polyhedra to the infinite-dimensional Gomory-Johnson model. These notions were known to coincide for continuous piecewise linear functions with rational breakpoints. We show that two of the notions, extreme functions and facets, coincide for the case of continuous piecewise linear functions, removing the hypothesis regarding rational breakpoints. We prove an if-and-only-if version of the Gomory-Johnson Facet Theorem. Finally, we separate the three notions using discontinuous examples.

math.OC↗
arXiv2019

Temporal Action Localization using Long Short-Term Dependency

Temporal action localization in untrimmed videos is an important but difficult task. Difficulties are encountered in the application of existing methods when modeling temporal structures of videos. In the present study, we developed a novel method, referred to as Gemini Network, for effective modeling of temporal structures and achieving high-performance temporal action localization. The significant improvements afforded by the proposed method are attributable to three major factors. First, the developed network utilizes two subnets for effective modeling of temporal structures. Second, three parallel feature extraction pipelines are used to prevent interference between the extractions of different stage features. Third, the proposed method utilizes auxiliary supervision, with the auxiliary classifier losses affording additional constraints for improving the modeling capability of the network. As a demonstration of its effectiveness, the Gemini Network was used to achieve state-of-the-art temporal action localization performance on two challenging datasets, namely, THUMOS14 and ActivityNet.

cs.CV↗
arXiv2019

Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking

In general, image restoration involves mapping from low quality images to their high-quality counterparts. Such optimal mapping is usually non-linear and learnable by machine learning. Recently, deep convolutional neural networks have proven promising for such learning processing. It is desirable for an image processing network to support well with three vital tasks, namely, super-resolution, denoising, and deblocking. It is commonly recognized that these tasks have strong correlations. Therefore, it is imperative to harness the inter-task correlations. To this end, we propose the cross-scale residual network to exploit scale-related features and the inter-task correlations among the three tasks. The proposed network can extract multiple spatial scale features and establish multiple temporal feature reusage. Our experiments show that the proposed approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations for multiple image restoration tasks.

eess.IV↗
arXiv2019

Comb Convolution for Efficient Convolutional Architecture

Convolutional neural networks (CNNs) are inherently suffering from massively redundant computation (FLOPs) due to the dense connection pattern between feature maps and convolution kernels. Recent research has investigated the sparse relationship between channels, however, they ignored the spatial relationship within a channel. In this paper, we present a novel convolutional operator, namely comb convolution, to exploit the intra-channel sparse relationship among neurons. The proposed convolutional operator eliminates nearly 50% of connections by inserting uniform mappings into standard convolutions and removing about half of spatial connections in convolutional layer. Notably, our work is orthogonal and complementary to existing methods that reduce channel-wise redundancy. Thus, it has great potential to further increase efficiency through integrating the comb convolution to existing architectures. Experimental results demonstrate that by simply replacing standard convolutions with comb convolutions on state-of-the-art CNN architectures (e.g., VGGNets, Xception and SE-Net), we can achieve 50% FLOPs reduction while still maintaining the accuracy.

cs.CV↗
arXiv2019

Channel Gating Neural Networks

This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channel gating identifies regions in the features that contribute less to the classification result, and skips the computation on a subset of the input channels for these ineffective regions. Unlike static network pruning, channel gating optimizes CNN inference at run-time by exploiting input-specific characteristics, which allows substantially reducing the compute cost with almost no accuracy loss. We experimentally show that applying channel gating in state-of-the-art networks achieves 2.7-8.0$\times$ reduction in floating-point operations (FLOPs) and 2.0-4.4$\times$ reduction in off-chip memory accesses with a minimal accuracy loss on CIFAR-10. Combining our method with knowledge distillation reduces the compute cost of ResNet-18 by 2.6$\times$ without accuracy drop on ImageNet. We further demonstrate that channel gating can be realized in hardware efficiently. Our approach exhibits sparsity patterns that are well-suited to dense systolic arrays with minimal additional hardware. We have designed an accelerator for channel gating networks, which can be implemented using either FPGAs or ASICs. Running a quantized ResNet-18 model for ImageNet, our accelerator achieves an encouraging speedup of 2.4$\times$ on average, with a theoretical FLOP reduction of 2.8$\times$.

cs.LG↗
arXiv2019

Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Bandits

Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning. In this paper we study the distributed version of this problem where we have multiple agents, and they want to learn the best arm collaboratively. We want to quantify the power of collaboration under limited interaction (or, communication steps), as interaction is expensive in many settings. We measure the running time of a distributed algorithm as the speedup over the best centralized algorithm where there is only one agent. We give almost tight round-speedup tradeoffs for this problem, along which we develop several new techniques for proving lower bounds on the number of communication steps under time or confidence constraints.

cs.LG↗
arXiv2019

Second order regularity for elliptic and parabolic equations involving $p$-Laplacian via a fundamental inequality

Denote by $Δ$ the Laplacian and by $Δ_\infty $ the $\infty$-Laplacian. A fundamental inequality is proved for the algebraic structure of $ΔvΔ_\infty v$: for every $v\in C^\infty$, $$\ | { |D^2vDv|^2} - {Δv Δ_\infty v } -\frac12[|D^2v|^2-(Δv)^2]|Dv|^2\ | \le \frac{n-2}2 [|D^2v|^2{|Dv|^2}- |D^2vDv|^2 ]. $$ Based on this, we prove the following results: 1. For any $p$-harmonic functions $u$, $p\in(1,2)\cup(2,\infty)$, we have $$|Du|^{\frac{p-γ}2}Du\in W^{1,2}_{\rm loc},$$ with $γ<\min\{p+\frac{n-1}{n},3+\frac{p-1}{n-1}\}$. As a by-product, when $p\in(1,2)\cup(2,3+\frac2{n-2})$, we reprove the known $W^{2,q}_{\rm loc}$-regularity of $p$-harmonic functions for some $q>2$. 2. When $n\ge 2$ and $p\in(1,2)\cup(2,3+\frac2{n-2})$, the viscosity solutions to parabolic normalized $p $-Laplace equation have the $W_{\rm loc}^{2,q}$-regularity in the spatial variable and the $W_{\rm loc}^{1,q}$-regularity in the time variable for some $q>2$. Especially, when $n=2$ an open question in [17] is completely answered. 3. When $n\ge 1 $ and $p\in(1,2)\cup(2,3)$, the weak/viscosity solutions to parabolic $p $-Laplace equation have the $W_{\rm loc}^{2,2}$-regularity in the spatial variable and the $W_{\rm loc}^{1,2}$-regularity in the time variable. The range of $p$ (including $p=2$ from the classical result) here is sharp for the $W_{\rm loc}^{2,2}$-regularity.

math.AP↗
arXiv2019

Graph Neural Network for Interpreting Task-fMRI Biomarkers

Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain networks constructed by fMRI. One way to interpret important features is through looking at how the classification probability changes if the features are occluded or replaced. The major limitation of this approach is that replacing values may change the distribution of the data and lead to serious errors. Therefore, we develop a 2-stage pipeline to eliminate the need to replace features for reliable biomarker interpretation. Specifically, we propose an inductive GNN to embed the graphs containing different properties of task-fMRI for identifying ASD and then discover the brain regions/sub-graphs used as evidence for the GNN classifier. We first show GNN can achieve high accuracy in identifying ASD. Next, we calculate the feature importance scores using GNN and compare the interpretation ability with Random Forest. Finally, we run with different atlases and parameters, proving the robustness of the proposed method. The detected biomarkers reveal their association with social behaviors. We also show the potential of discovering new informative biomarkers. Our pipeline can be generalized to other graph feature importance interpretation problems.

cs.LG↗
arXiv2019

HGC: Hierarchical Group Convolution for Highly Efficient Neural Network

Group convolution works well with many deep convolutional neural networks (CNNs) that can effectively compress the model by reducing the number of parameters and computational cost. Using this operation, feature maps of different group cannot communicate, which restricts their representation capability. To address this issue, in this work, we propose a novel operation named Hierarchical Group Convolution (HGC) for creating computationally efficient neural networks. Different from standard group convolution which blocks the inter-group information exchange and induces the severe performance degradation, HGC can hierarchically fuse the feature maps from each group and leverage the inter-group information effectively. Taking advantage of the proposed method, we introduce a family of compact networks called HGCNets. Compared to networks using standard group convolution, HGCNets have a huge improvement in accuracy at the same model size and complexity level. Extensive experimental results on the CIFAR dataset demonstrate that HGCNets obtain significant reduction of parameters and computational cost to achieve comparable performance over the prior CNN architectures designed for mobile devices such as MobileNet and ShuffleNet.

cs.CV↗
arXiv2019

Thresholding Bandit with Optimal Aggregate Regret

We consider the thresholding bandit problem, whose goal is to find arms of mean rewards above a given threshold $θ$, with a fixed budget of $T$ trials. We introduce LSA, a new, simple and anytime algorithm that aims to minimize the aggregate regret (or the expected number of mis-classified arms). We prove that our algorithm is instance-wise asymptotically optimal. We also provide comprehensive empirical results to demonstrate the algorithm's superior performance over existing algorithms under a variety of different scenarios.

cs.LG↗
arXiv2019

C^1-Regularity of planar \infty-harmonic functions - REVISIT

In the seminal paper [Arch. Ration. Mech. Anal. 176 (2005), 351--361], Savin proved the $C^1$-regularity of planar $\infty$-harmonic functions $u$. Here we give a new understanding of it from a capacity viewpoint and drop several high technique arguments therein. Our argument is essentially based on a topological lemma of Savin, a flat estimate by Evans and Smart, % \cite{es11a}, $W^{1,2}_{loc}$-regularity of $|Du|$ and Crandall's flow for infinity harmonic functions.

math.AP↗
arXiv2019

All Cyclic Group Facets Inject

We give a variant of Basu-Hildebrand-Molinaro's approximation theorem for continuous minimal valid functions for Gomory-Johnson's infinite group problem by piecewise linear two-slope extreme functions [Minimal cut-generating functions are nearly extreme, IPCO 2016]. Our theorem is for piecewise linear minimal valid functions that have only rational breakpoints (in $1/q\,\mathbb{Z}$ for some $q\in \mathbb{N}$) and that take rational values at the breakpoints. In contrast to Basu et al.'s construction, our construction preserves all function values on $1/q\,\mathbb{Z}$. As a corollary, we obtain that every extreme function for the finite group problem on $1/q\,\mathbb{Z}$ is the restriction of a continuous piecewise linear two-slope extreme function for the infinite group problem with breakpoints on a refinement $1/(Mq)\,\mathbb{Z}$ for some $M\in \mathbb{N}$. In combination with Gomory's master theorem [Some Polyhedra related to Combinatorial Problems, Lin. Alg. Appl. 2 (1969), 451-558], this shows that the infinite group problem is the correct master problem for facets (extreme functions) of 1-row group relaxations.

math.GR↗
arXiv2019

Interfacing a topological qubit with a spin qubit in a hybrid quantum system

We present and analyze a hybrid quantum system that interfaces a Majorana-hosted semiconductor nanowire with a single nitrogen-vacancy (NV) center via a magnetized torsional cantilever. We show that, the torsional mode of the mechanical resonator can strongly couple to the Majorana qubit and the spin qubit simultaneously, which allows to interface them for quantum state conversion through a dark state protocol. This work provides a promising interface between the topological qubit and the conventional spin qubit, and can find interesting applications in quantum information and computation.

quant-ph↗
arXiv2019

Efficient Interpretation of Deep Learning Models Using Graph Structure and Cooperative Game Theory: Application to ASD Biomarker Discovery

Discovering imaging biomarkers for autism spectrum disorder (ASD) is critical to help explain ASD and predict or monitor treatment outcomes. Toward this end, deep learning classifiers have recently been used for identifying ASD from functional magnetic resonance imaging (fMRI) with higher accuracy than traditional learning strategies. However, a key challenge with deep learning models is understanding just what image features the network is using, which can in turn be used to define the biomarkers. Current methods extract biomarkers, i.e., important features, by looking at how the prediction changes if "ignoring" one feature at a time. In this work, we go beyond looking at only individual features by using Shapley value explanation (SVE) from cooperative game theory. Cooperative game theory is advantageous here because it directly considers the interaction between features and can be applied to any machine learning method, making it a novel, more accurate way of determining instance-wise biomarker importance from deep learning models. A barrier to using SVE is its computational complexity: $2^N$ given $N$ features. We explicitly reduce the complexity of SVE computation by two approaches based on the underlying graph structure of the input data: 1) only consider the centralized coalition of each feature; 2) a hierarchical pipeline which first clusters features into small communities, then applies SVE in each community. Monte Carlo approximation can be used for large permutation sets. We first validate our methods on the MNIST dataset and compare to human perception. Next, to insure plausibility of our biomarker results, we train a Random Forest (RF) to classify ASD/control subjects from fMRI and compare SVE results to standard RF-based feature importance. Finally, we show initial results on ranked fMRI biomarkers using SVE on a deep learning classifier for the ASD/control dataset.

cs.CV↗
arXiv2019

LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models

We develop a new Low-level, First-order Probabilistic Programming Language (LF-PPL) suited for models containing a mix of continuous, discrete, and/or piecewise-continuous variables. The key success of this language and its compilation scheme is in its ability to automatically distinguish parameters the density function is discontinuous with respect to, while further providing runtime checks for boundary crossings. This enables the introduction of new inference engines that are able to exploit gradient information, while remaining efficient for models which are not everywhere differentiable. We demonstrate this ability by incorporating a discontinuous Hamiltonian Monte Carlo (DHMC) inference engine that is able to deliver automated and efficient inference for non-differentiable models. Our system is backed up by a mathematical formalism that ensures that any model expressed in this language has a density with measure zero discontinuities to maintain the validity of the inference engine.

cs.LG↗
arXiv2019

An Optimal Policy for Dynamic Assortment Planning Under Uncapacitated Multinomial Logit Models

We study the dynamic assortment planning problem, where for each arriving customer, the seller offers an assortment of substitutable products and customer makes the purchase among offered products according to an uncapacitated multinomial logit (MNL) model. Since all the utility parameters of MNL are unknown, the seller needs to simultaneously learn customers' choice behavior and make dynamic decisions on assortments based on the current knowledge. The goal of the seller is to maximize the expected revenue, or equivalently, to minimize the expected regret. Although dynamic assortment planning problem has received an increasing attention in revenue management, most existing policies require the estimation of mean utility for each product and the final regret usually involves the number of products $N$. The optimal regret of the dynamic assortment planning problem under the most basic and popular choice model---MNL model is still open. By carefully analyzing a revenue potential function, we develop a trisection based policy combined with adaptive confidence bound construction, which achieves an {item-independent} regret bound of $O(\sqrt{T})$, where $T$ is the length of selling horizon. We further establish the matching lower bound result to show the optimality of our policy. There are two major advantages of the proposed policy. First, the regret of all our policies has no dependence on $N$. Second, our policies are almost assumption free: there is no assumption on mean utility nor any "separability" condition on the expected revenues for different assortments. Our result also extends the unimodal bandit literature.

stat.ML↗