We examine Dropout through the perspective of interactions. This view provides a symmetry to explain Dropout: given $N$ variables, there are ${N \choose k}$ possible sets of $k$ variables to form an interaction (i.e. $\mathcal{O}(N^k)$); conversely, the probability an interaction of $k$ variables survives Dropout at rate $p$ is $(1-p)^k$ (decaying with $k$). These rates effectively cancel, and so Dropout regularizes against higher-order interactions. We prove this perspective analytically and empirically. This perspective of Dropout as a regularizer against interaction effects has several practical implications: (1) higher Dropout rates should be used when we need stronger regularization against spurious high-order interactions, (2) caution should be exercised when interpreting Dropout-based explanations and uncertainty measures, and (3) networks trained with Input Dropout are biased estimators. We also compare Dropout to other regularizers and find that it is difficult to obtain the same selective pressure against high-order interactions.
Istituto Italiano di Tecnologia（意大利技术研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretical analysis of dropout for MF, where Bernoulli random variables are used to drop columns of the factors. We demonstrate the equivalence between dropout and a fully deterministic model for MF in which the…
We give a formal and complete characterization of the explicit regularizer induced by dropout in deep linear networks with squared loss. We show that (a) the explicit regularizer is composed of an $\ell_2$-path regularizer and other terms that are also re-scaling invariant, (b) the convex envelope of the induced regularizer is the squared nuclear norm of the network map, and (c) for a sufficiently large dropout rate, we characterize the global optima of the dropout objective. We validate our theoretical findings with empirical results.
Johns Hopkins University（约翰斯·霍普金斯大学）；University of California, Berkeley（加州大学伯克利分校）；TTI Chicago（芝加哥丰田技术研究所）
We investigate the capacity control provided by dropout in various machine learning problems. First, we study dropout for matrix completion, where it induces a data-dependent regularizer that, in expectation, equals the weighted trace-norm of the product of the factors. In deep learning, we show that the data-dependent regularizer due to dropout directly controls the Rademacher complexity of the underlying class of deep neural networks. These developments enable us to give concrete generalization error bounds for the dropout algorithm in both matrix completion as well as training deep neural n…
University of Liverpool（利物浦大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）
While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking. We introduce the concept of \emph{weight expansion}, an increase in the signed volume of a parallelotope spanned by the column or row vectors of the weight covariance matrix, and show that weight expansion is an effective means of increasing the generalization in a PAC-Bayesian setting. We provide a theoretical argument that dropout leads to weight expansion and extensive empirical support for the correlation between dropout and weight expansion. To supp…
Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout regularizer is first-order equivalent to an L2 regularizer applied after scaling the features by an estimate of the inverse diagonal Fisher information matrix. We also establish a connection to AdaGrad, an online learning algorithm, and find that a close relative of AdaGrad operates by repeatedly solving linear dropout-regularized problems. By casting dropout …
Clova AI Research, NAVER Corp.（NAVER公司Clova AI研究中心）；KAIST（韩国科学技术院）；AI Center, SK Telecom（SK电讯AI中心）
Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to these demands, but we conjecture that the dropout on RNNs could have been improved by adopting the adversarial concept. This paper investigates ways to improve the dropout for RNNs by utilizing intentionally generated dropout masks. Specifically, the guided dropout used in this research is called as adversarial dropout, which adversarially disconnects neurons that are dominantly…
Deep Neural Networks often require good regularizers to generalize well. Dropout is one such regularizer that is widely used among Deep Learning practitioners. Recent work has shown that Dropout can also be viewed as performing Approximate Bayesian Inference over the network parameters. In this work, we generalize this notion and introduce a rich family of regularizers which we call Generalized Dropout. One set of methods in this family, called Dropout++, is a version of Dropout with trainable parameters. Classical Dropout emerges as a special case of this method. Another member of this family…
Virginia Tech（弗吉尼亚理工大学）；Université de Montréal（蒙特利尔大学）；Facebook AI Research (FAIR)（脸书人工智能研究院）；Microsoft Research（微软研究院）
One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of training data. In this work, we propose a new regularizer called DeCov which leads to significantly reduced overfitting (as indicated by the difference between train and val performance), and better generalization. Our regularizer encourages diverse or non-redundant representations in Deep Neural Networks by minimizing the cross-covariance of hidden activat…
Stanford University（斯坦福大学）；Microsoft Research（微软研究院）；University of Washington（华盛顿大学）
Dropout is a widely-used regularization technique, often required to obtain state-of-the-art for a number of architectures. This work demonstrates that dropout introduces two distinct but entangled regularization effects: an explicit effect (also studied in prior work) which occurs since dropout modifies the expected training objective, and, perhaps surprisingly, an additional implicit effect from the stochasticity in the dropout training update. This implicit regularization effect is analogous to the effect of stochasticity in small mini-batch stochastic gradient descent. We disentangle these…
We formalize the notion of a pseudo-ensemble, a (possibly infinite) collection of child models spawned from a parent model by perturbing it according to some noise process. E.g., dropout (Hinton et. al, 2012) in a deep neural network trains a pseudo-ensemble of child subnetworks generated by randomly masking nodes in the parent network. We present a novel regularizer based on making the behavior of a pseudo-ensemble robust with respect to the noise process generating it. In the fully-supervised setting, our regularizer matches the performance of dropout. But, unlike dropout, our regularizer na…
Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager, et.al. We focus on linear classification where a convex proxy to the misclassification loss (i.e. the logistic loss used in logistic regression) is minimized. We show: (a) when the dropout-regularized criterion has a unique minimizer, (b) when the dropout-regularization penalty …
We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can also be viewed as doing matrix factorization using a particular regularizer. Dropout algorithms such as these are thus regularization techniques that use 0,1-valued random variables to filter weights during training in order to avoid coadaptation of features. By leveraging a recent result on nonconvex optimization and conducting a careful analysis of the set of minimizers as well as the Hessian of the loss function, …
Deep neural networks are over-parameterized, which implies that the number of parameters are much larger than the number of samples used to train the network. Even in such a regime deep architectures do not overfit. This phenomenon is an active area of research and many theories have been proposed trying to understand this peculiar observation. These include the Vapnik Chervonenkis (VC) dimension bounds and Rademacher complexity bounds which show that the capacity of the network is characterized by the norm of weights rather than the number of parameters. However, the effect of input noise on …
FlexiDrop: Theoretical Insights and Practical Advances in Random Dropout Method on GNNs
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）；School of Mathematical Sciences, University of Chinese Academy of Sciences（中国科学院大学数学科学学院）；School of Mathematics and Statistics, Guangdong University of Technology（广东工业大学数学与统计学院）
Shanghai Jiao Tong University（上海交通大学）；Sun Yat-sen University（中山大学）；Huazhong University of Science and Technology（华中科技大学）
This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretic interactions. We prove that dropout can suppress the strength of interactions between input variables of deep neural networks (DNNs). The theoretic proof is also verified by various experiments. Furthermore, we find that such interactions were strongly related to the over-fitting problem in deep learning. Thus, the utility of dropout can be regarded as decreasing interactions to alleviate the significance of over-fitting. Based on this understanding, we propose an interaction l…
University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）；Paige AI；Tencent AI Lab（腾讯人工智能实验室）
Regularizers help deep neural networks prevent feature co-adaptations. Dropout, as a commonly used regularization technique, stochastically disables neuron activations during network optimization. However, such complete feature disposal can affect the feature representation and network understanding. Toward better descriptions of latent representations, we present DropGraph that learns a regularization function by constructing a stand-alone graph from the backbone features. DropGraph first samples stochastic spatial feature vectors and then incorporates graph reasoning methods to generate feat…
Factorization machines (FMs) are machine learning predictive models based on second-order feature interactions and FMs with sparse regularization are called sparse FMs. Such regularizations enable feature selection, which selects the most relevant features for accurate prediction, and therefore they can contribute to the improvement of the model accuracy and interpretability. However, because FMs use second-order feature interactions, the selection of features often causes the loss of many relevant feature interactions in the resultant models. In such cases, FMs with regularization specially d…
Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates. While traditional systems interacting with students suffered from data sparsity and overfitting, recent sample-level contrastive learning helps to alleviate this issue. One major limitation of sample-level approaches is that they regard students' behavior interaction sequences as a bundle, so they often fail to encode temporal contexts and track their dynamic changes, making it hard to find optimal representations for knowledge tracing and dropout predic…
Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence on the learning (like denoising and dropout rate) and structural (like depth and layer lengths) aspects of the network is less mature. An interesting question in this context is to ask if the network structure could "guide" the choices of such learning parameters. In this work, we explore these gaps between network structure, the learning mechanisms and thei…
LIT-LVM: Structured Regularization for Interaction Terms in Linear Predictors using Latent Variable Models
Department of Computer and Data Sciences（计算机与数据科学系）；Case Western Reserve University（凯斯西储大学）；Department of Mathematics and Computer Science（数学与计算机科学系）；Suffolk University（索尔福德大学）
Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric information game with no such model or interaction. Our approach is to encourage an agent to reveal or hide their intentions using an information-theoretic regularizer. We consider both the mutual information between goal and action given state, as well as the mutual information between …
Microsoft R&D, India（微软研发中心，印度）；BITS Pilani, Goa, India（比拉尼大学果阿分校，印度）
Long-Short-Term-Memory (LSTM) networks have shown great promise in artificial intelligence (AI) based language modeling. Recently, LSTM networks have also become popular for designing AI-based Intrusion Detection Systems (IDS). However, its applicability in IDS is studied largely in the default settings as used in language models. Whereas security applications offer distinct conditions and hence warrant careful consideration while applying such recurrent networks. Therefore, we conducted one of the most exhaustive works on LSTM hyper-parameters for IDS and experimented with approx. 150 LSTM co…
