arXiv subjects

Yang Yuan

Publications and source records attributed to Yang Yuan.

At least 55 records · Page 3Linked to original sources

arXiv2020

Imbalance Robust Softmax for Deep Embeeding Learning

Deep embedding learning is expected to learn a metric space in which features have smaller maximal intra-class distance than minimal inter-class distance. In recent years, one research focus is to solve the open-set problem by discriminative deep embedding learning in the field of face recognition (FR) and person re-identification (re-ID). Apart from open-set problem, we find that imbalanced training data is another main factor causing the performance degradation of FR and re-ID, and data imbalance widely exists in the real applications. However, very little research explores why and how data imbalance influences the performance of FR and re-ID with softmax or its variants. In this work, we deeply investigate data imbalance in the perspective of neural network optimisation and feature distribution about softmax. We find one main reason of performance degradation caused by data imbalance is that the weights (from the penultimate fully-connected layer) are far from their class centers in feature space. Based on this investigation, we propose a unified framework, Imbalance-Robust Softmax (IR-Softmax), which can simultaneously solve the open-set problem and reduce the influence of data imbalance. IR-Softmax can generalise to any softmax and its variants (which are discriminative for open-set problem) by directly setting the weights as their class centers, naturally solving the data imbalance problem. In this work, we explicitly re-formulate two discriminative softmax (A-Softmax and AM-Softmax) under the framework of IR-Softmax. We conduct extensive experiments on FR databases (LFW, MegaFace) and re-ID database (Market-1501, Duke), and IR-Softmax outperforms many state-of-the-art methods.

cs.CV↗

arXiv2020

Secure Data Sharing With Flow Model

In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data. We consider a variant of this problem, where the input data can be shared for machine learning training purposes, but the data are also encrypted so that they cannot be recovered by other parties. We present a rotation based method using flow model, and theoretically justified its security. We demonstrate the effectiveness of our method in different scenarios, including supervised secure model training, and unsupervised generative model training. Our code is available at https://github.com/ duchenzhuang/flowencrypt.

cs.LG↗

arXiv2020

Inject Machine Learning into Significance Test for Misspecified Linear Models

Due to its strong interpretability, linear regression is widely used in social science, from which significance test provides the significance level of models or coefficients in the traditional statistical inference. However, linear regression methods rely on the linear assumptions of the ground truth function, which do not necessarily hold in practice. As a result, even for simple non-linear cases, linear regression may fail to report the correct significance level. In this paper, we present a simple and effective assumption-free method for linear approximation in both linear and non-linear scenarios. First, we apply a machine learning method to fit the ground truth function on the training set and calculate its linear approximation. Afterward, we get the estimator by adding adjustments based on the validation set. We prove the concentration inequalities and asymptotic properties of our estimator, which leads to the corresponding significance test. Experimental results show that our estimator significantly outperforms linear regression for non-linear ground truth functions, indicating that our estimator might be a better tool for the significance test.

cs.LG↗

arXiv2020

Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers

Strong theoretical guarantees of robustness can be given for ensembles of classifiers generated by input randomization. Specifically, an $\ell_2$ bounded adversary cannot alter the ensemble prediction generated by an additive isotropic Gaussian noise, where the radius for the adversary depends on both the variance of the distribution as well as the ensemble margin at the point of interest. We build on and considerably expand this work across broad classes of distributions. In particular, we offer adversarial robustness guarantees and associated algorithms for the discrete case where the adversary is $\ell_0$ bounded. Moreover, we exemplify how the guarantees can be tightened with specific assumptions about the function class of the classifier such as a decision tree. We empirically illustrate these results with and without functional restrictions across image and molecule datasets.

cs.LG↗

arXiv2020

Adversarial Data Encryption

In the big data era, many organizations face the dilemma of data sharing. Regular data sharing is often necessary for human-centered discussion and communication, especially in medical scenarios. However, unprotected data sharing may also lead to data leakage. Inspired by adversarial attack, we propose a method for data encryption, so that for human beings the encrypted data look identical to the original version, but for machine learning methods they are misleading. To show the effectiveness of our method, we collaborate with the Beijing Tiantan Hospital, which has a world leading neurological center. We invite $3$ doctors to manually inspect our encryption method based on real world medical images. The results show that the encrypted images can be used for diagnosis by the doctors, but not by machine learning methods.

cs.LG↗

arXiv2019

Learning-Based Low-Rank Approximations

We introduce a "learning-based" algorithm for the low-rank decomposition problem: given an $n \times d$ matrix $A$, and a parameter $k$, compute a rank-$k$ matrix $A'$ that minimizes the approximation loss $\|A-A'\|_F$. The algorithm uses a training set of input matrices in order to optimize its performance. Specifically, some of the most efficient approximate algorithms for computing low-rank approximations proceed by computing a projection $SA$, where $S$ is a sparse random $m \times n$ "sketching matrix", and then performing the singular value decomposition of $SA$. We show how to replace the random matrix $S$ with a "learned" matrix of the same sparsity to reduce the error. Our experiments show that, for multiple types of data sets, a learned sketch matrix can substantially reduce the approximation loss compared to a random matrix $S$, sometimes by one order of magnitude. We also study mixed matrices where only some of the rows are trained and the remaining ones are random, and show that matrices still offer improved performance while retaining worst-case guarantees. Finally, to understand the theoretical aspects of our approach, we study the special case of $m=1$. In particular, we give an approximation algorithm for minimizing the empirical loss, with approximation factor depending on the stable rank of matrices in the training set. We also show generalization bounds for the sketch matrix learning problem.

cs.LG↗

arXiv2019

System-Level Development of a User-Integrated Semi-Autonomous Lawn Mowing System: Problem Overview, Basic Requirements, and Proposed Architecture

This concept paper outlines some recent efforts toward the design and development of user-integrated semi-autonomous home-sized lawn mowing systems from a systems engineering perspective. This is an important and emerging field of study within the robotics and systems engineering communities. The work presented includes a review of current progress on this problem, a discussion of the problem from a systems engineering perspective, a general system architecture developed by the authors, and a preliminary set of design requirements. This work is meant to provide a baseline and motivation for the further development and refinement of these systems within the systems engineering and robotics communities and is relevant to both academic and commercial research.

cs.RO↗

arXiv2019

Asymmetric Valleys: Beyond Sharp and Flat Local Minima

Despite the non-convex nature of their loss functions, deep neural networks are known to generalize well when optimized with stochastic gradient descent (SGD). Recent work conjectures that SGD with proper configuration is able to find wide and flat local minima, which have been proposed to be associated with good generalization performance. In this paper, we observe that local minima of modern deep networks are more than being flat or sharp. Specifically, at a local minimum there exist many asymmetric directions such that the loss increases abruptly along one side, and slowly along the opposite side--we formally define such minima as asymmetric valleys. Under mild assumptions, we prove that for asymmetric valleys, a solution biased towards the flat side generalizes better than the exact minimizer. Further, we show that simply averaging the weights along the SGD trajectory gives rise to such biased solutions implicitly. This provides a theoretical explanation for the intriguing phenomenon observed by Izmailov et al. (2018). In addition, we empirically find that batch normalization (BN) appears to be a major cause for asymmetric valleys.

cs.LG↗

arXiv2018

An empirical study on evaluation metrics of generative adversarial networks

Evaluating generative adversarial networks (GANs) is inherently challenging. In this paper, we revisit several representative sample-based evaluation metrics for GANs, and address the problem of how to evaluate the evaluation metrics. We start with a few necessary conditions for metrics to produce meaningful scores, such as distinguishing real from generated samples, identifying mode dropping and mode collapsing, and detecting overfitting. With a series of carefully designed experiments, we comprehensively investigate existing sample-based metrics and identify their strengths and limitations in practical settings. Based on these results, we observe that kernel Maximum Mean Discrepancy (MMD) and the 1-Nearest-Neighbor (1-NN) two-sample test seem to satisfy most of the desirable properties, provided that the distances between samples are computed in a suitable feature space. Our experiments also unveil interesting properties about the behavior of several popular GAN models, such as whether they are memorizing training samples, and how far they are from learning the target distribution.

cs.LG↗

arXiv2018

An Alternative View: When Does SGD Escape Local Minima?

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order to understand this phenomenon, we take an alternative view that SGD is working on the convolved (thus smoothed) version of the loss function. We show that, even if the function $f$ has many bad local minima or saddle points, as long as for every point $x$, the weighted average of the gradients of its neighborhoods is one point convex with respect to the desired solution $x^*$, SGD will get close to, and then stay around $x^*$ with constant probability. More specifically, SGD will not get stuck at "sharp" local minima with small diameters, as long as the neighborhoods of these regions contain enough gradient information. The neighborhood size is controlled by step size and gradient noise. Our result identifies a set of functions that SGD provably works, which is much larger than the set of convex functions. Empirically, we observe that the loss surface of neural networks enjoys nice one point convexity properties locally, therefore our theorem helps explain why SGD works so well for neural networks.

cs.LG↗

arXiv2018

Hyperparameter Optimization: A Spectral Approach

We give a simple, fast algorithm for hyperparameter optimization inspired by techniques from the analysis of Boolean functions. We focus on the high-dimensional regime where the canonical example is training a neural network with a large number of hyperparameters. The algorithm --- an iterative application of compressed sensing techniques for orthogonal polynomials --- requires only uniform sampling of the hyperparameters and is thus easily parallelizable. Experiments for training deep neural networks on Cifar-10 show that compared to state-of-the-art tools (e.g., Hyperband and Spearmint), our algorithm finds significantly improved solutions, in some cases better than what is attainable by hand-tuning. In terms of overall running time (i.e., time required to sample various settings of hyperparameters plus additional computation time), we are at least an order of magnitude faster than Hyperband and Bayesian Optimization. We also outperform Random Search 8x. Additionally, our method comes with provable guarantees and yields the first improvements on the sample complexity of learning decision trees in over two decades. In particular, we obtain the first quasi-polynomial time algorithm for learning noisy decision trees with polynomial sample complexity.

cs.LG↗

arXiv2017

Convergence Analysis of Two-layer Neural Networks with ReLU Activation

In recent years, stochastic gradient descent (SGD) based techniques has become the standard tools for training neural networks. However, formal theoretical understanding of why SGD can train neural networks in practice is largely missing. In this paper, we make progress on understanding this mystery by providing a convergence analysis for SGD on a rich subset of two-layer feedforward networks with ReLU activations. This subset is characterized by a special structure called "identity mapping". We prove that, if input follows from Gaussian distribution, with standard $O(1/\sqrt{d})$ initialization of the weights, SGD converges to the global minimum in polynomial number of steps. Unlike normal vanilla networks, the "identity mapping" makes our network asymmetric and thus the global minimum is unique. To complement our theory, we are also able to show experimentally that multi-layer networks with this mapping have better performance compared with normal vanilla networks. Our convergence theorem differs from traditional non-convex optimization techniques. We show that SGD converges to optimal in "two phases": In phase I, the gradient points to the wrong direction, however, a potential function $g$ gradually decreases. Then in phase II, SGD enters a nice one point convex region and converges. We also show that the identity mapping is necessary for convergence, as it moves the initial point to a better place for optimization. Experiment verifies our claims.

cs.LG↗

arXiv2016

Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters

The amount of data available in the world is growing faster than our ability to deal with it. However, if we take advantage of the internal \emph{structure}, data may become much smaller for machine learning purposes. In this paper we focus on one of the fundamental machine learning tasks, empirical risk minimization (ERM), and provide faster algorithms with the help from the clustering structure of the data. We introduce a simple notion of raw clustering that can be efficiently computed from the data, and propose two algorithms based on clustering information. Our accelerated algorithm ClusterACDM is built on a novel Haar transformation applied to the dual space of the ERM problem, and our variance-reduction based algorithm ClusterSVRG introduces a new gradient estimator using clustering. Our algorithms outperform their classical counterparts ACDM and SVRG respectively.

cs.LG↗

arXiv2016

Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives

Many classical algorithms are found until several years later to outlive the confines in which they were conceived, and continue to be relevant in unforeseen settings. In this paper, we show that SVRG is one such method: being originally designed for strongly convex objectives, it is also very robust in non-strongly convex or sum-of-non-convex settings. More precisely, we provide new analysis to improve the state-of-the-art running times in both settings by either applying SVRG or its novel variant. Since non-strongly convex objectives include important examples such as Lasso or logistic regression, and sum-of-non-convex objectives include famous examples such as stochastic PCA and is even believed to be related to training deep neural nets, our results also imply better performances in these applications.

cs.LG↗

arXiv2016

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling

Accelerated coordinate descent is widely used in optimization due to its cheap per-iteration cost and scalability to large-scale problems. Up to a primal-dual transformation, it is also the same as accelerated stochastic gradient descent that is one of the central methods used in machine learning. In this paper, we improve the best known running time of accelerated coordinate descent by a factor up to $\sqrt{n}$. Our improvement is based on a clean, novel non-uniform sampling that selects each coordinate with a probability proportional to the square root of its smoothness parameter. Our proof technique also deviates from the classical estimation sequence technique used in prior work. Our speed-up applies to important problems such as empirical risk minimization and solving linear systems, both in theory and in practice.

math.OC↗

arXiv2016

Optimization Algorithms for Faster Computational Geometry

We study two fundamental problems in computational geometry: finding the maximum inscribed ball (MaxIB) inside a bounded polyhedron defined by $m$ hyperplanes, and the minimum enclosing ball (MinEB) of a set of $n$ points, both in $d$-dimensional space. We improve the running time of iterative algorithms on MaxIB from $\tilde{O}(m d α^3 / \varepsilon^3)$ to $\tilde{O}(md + m \sqrt{d} α/ \varepsilon)$, a speed-up up to $\tilde{O}(\sqrt{d} α^2 / \varepsilon^2)$, and MinEB from $\tilde{O}(n d / \sqrt{\varepsilon})$ to $\tilde{O}(nd + n \sqrt{d} / \sqrt{\varepsilon})$, a speed-up up to $\tilde{O}(\sqrt{d})$. Our improvements are based on a novel saddle-point optimization framework. We propose a new algorithm $\mathtt{L1L2SPSolver}$ for solving a class of regularized saddle-point problems, and apply a randomized Hadamard space rotation which is a technique borrowed from compressive sensing. Interestingly, the motivation of using Hadamard rotation solely comes from our optimization view but not the original geometry problem: indeed, it is not immediately clear why MaxIB or MinEB, as a geometric problem, should be easier to solve if we rotate the space by a unitary matrix. We hope that our optimization perspective sheds lights on solving other geometric problems as well.

cs.CG↗

arXiv2016

Simultaneous Nearest Neighbor Search

Motivated by applications in computer vision and databases, we introduce and study the Simultaneous Nearest Neighbor Search (SNN) problem. Given a set of data points, the goal of SNN is to design a data structure that, given a collection of queries, finds a collection of close points that are compatible with each other. Formally, we are given $k$ query points $Q=q_1,\cdots,q_k$, and a compatibility graph $G$ with vertices in $Q$, and the goal is to return data points $p_1,\cdots,p_k$ that minimize (i) the weighted sum of the distances from $q_i$ to $p_i$ and (ii) the weighted sum, over all edges $(i,j)$ in the compatibility graph $G$, of the distances between $p_i$ and $p_j$. The problem has several applications, where one wants to return a set of consistent answers to multiple related queries. This generalizes well-studied computational problems, including NN, Aggregate NN and the 0-extension problem. In this paper we propose and analyze the following general two-step method for designing efficient data structures for SNN. In the first step, for each query point $q_i$ we find its (approximate) nearest neighbor point $\hat{p}_i$; this can be done efficiently using existing approximate nearest neighbor structures. In the second step, we solve an off-line optimization problem over sets $q_1,\cdots,q_k$ and $\hat{p}_1,\cdots,\hat{p}_k$; this can be done efficiently given that $k$ is much smaller than $n$. Even though $\hat{p}_1,\cdots,\hat{p}_k$ might not constitute the optimal answers to queries $q_1,\cdots,q_k$, we show that, for the unweighted case, the resulting algorithm is $O(\log k/\log \log k)$-approximation. Also, we show that the approximation factor can be in fact reduced to a constant for compatibility graphs frequently occurring in practice. Finally, we show that the "empirical approximation factor" provided by the above approach is very close to 1.

cs.DS↗

arXiv2016

Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Arms

We define a general framework for a large class of combinatorial multi-armed bandit (CMAB) problems, where subsets of base arms with unknown distributions form super arms. In each round, a super arm is played and the base arms contained in the super arm are played and their outcomes are observed. We further consider the extension in which more based arms could be probabilistically triggered based on the outcomes of already triggered arms. The reward of the super arm depends on the outcomes of all played arms, and it only needs to satisfy two mild assumptions, which allow a large class of nonlinear reward instances. We assume the availability of an offline (α,β)-approximation oracle that takes the means of the outcome distributions of arms and outputs a super arm that with probability β generates an α fraction of the optimal expected reward. The objective of an online learning algorithm for CMAB is to minimize (α,β)-approximation regret, which is the difference between the αβ fraction of the expected reward when always playing the optimal super arm, and the expected reward of playing super arms according to the algorithm. We provide CUCB algorithm that achieves O(log n) distribution-dependent regret, where n is the number of rounds played, and we further provide distribution-independent bounds for a large class of reward functions. Our regret analysis is tight in that it matches the bound of UCB1 algorithm (up to a constant factor) for the classical MAB problem, and it significantly improves the regret bound in a earlier paper on combinatorial bandits with linear rewards. We apply our CMAB framework to two new applications, probabilistic maximum coverage and social influence maximization, both having nonlinear reward structures. In particular, application to social influence maximization requires our extension on probabilistically triggered arms.

cs.LG↗