Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it impacts over-parameterized, deep neural networks. This work is inspired by recent theoretical results showing that on (linearly) separable data, deep linear networks optimized by SGD learn weight-agnostic solutions, prompting us to ask, for realistic deep networks, for which many practical datasets are separable, what is the effect of importance weighting? We present the surprising finding that while importance weighting impacts models early in training, its effect diminishes over successive epochs. Moreover, while L2 regularization and batch normalization (but not dropout), restore some of the impact of importance weighting, they express the effect via (seemingly) the wrong abstraction: why should practitioners tweak the L2 regularization, and by how much, to produce the correct weighting effect? Our experiments confirm these findings across a range of architectures and datasets.
A key assumption in supervised learning is that training and test data follow the same probability distribution. However, this fundamental assumption is not always satisfied in practice, e.g., due to changing environments, sample selection bias, privacy concerns, or high labeling costs. Transfer learning (TL) relaxes this assumption and allows us to learn under distribution shift. Classical TL methods typically rely on importance-weighting -- a predictor is trained based on the training losses weighted according to the importance (i.e., the test-over-training density ratio). However, as real-w…
We propose a sample-efficient alternative for importance weighting for situations where one only has sample access to the probability distribution that generates the observations. Our new method, called Geometric Resampling (GR), is described and analyzed in the context of online combinatorial optimization under semi-bandit feedback, where a learner sequentially selects its actions from a combinatorial decision set so as to minimize its cumulative loss. In particular, we show that the well-known Follow-the-Perturbed-Leader (FPL) prediction method coupled with Geometric Resampling yields the fi…
We consider off-policy evaluation in the contextual bandit setting for the purpose of obtaining a robust off-policy selection strategy, where the selection strategy is evaluated based on the value of the chosen policy in a set of proposal (target) policies. We propose a new method to compute a lower bound on the value of an arbitrary target policy given some logged data in contextual bandits for a desired coverage. The lower bound is built around the so-called Self-normalized Importance Weighting (SN) estimator. It combines the use of a semi-empirical Efron-Stein tail inequality to control the…
CyberAgent, Inc.（赛博代理公司）；The University of Tokyo（东京大学）；Temple University（天普大学）
We consider learning causal relationships under conditional moment restrictions. Unlike causal inference under unconditional moment restrictions, conditional moment restrictions pose serious challenges for causal inference, especially in high-dimensional settings. To address this issue, we propose a method that transforms conditional moment restrictions to unconditional moment restrictions through importance weighting, using a conditional density ratio estimator. Using this transformation, we successfully estimate nonparametric functions defined under conditional moment restrictions. Our propo…
University of Copenhagen（哥本哈根大学）；Delft University of Technology（代尔夫特理工大学）
Importance weighting is widely applicable in machine learning in general and in techniques dealing with data covariate shift problems in particular. A novel, direct approach to determine such importance weighting is presented. It relies on a nearest neighbor classification scheme and is relatively straightforward to implement. Comparative experiments on various classification tasks demonstrate the effectiveness of our so-called nearest neighbor weighting (NNeW) scheme. Considering its performance, our procedure can act as a simple and effective baseline method for importance weighting.
Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of data manipulation. In this work, we propose a new method that supports learning different manipulation schemes with the same gradient-based algorithm. Our approach builds upon a recent connection of supervised learning and reinforcement learning (RL), and adapts an off-the-shelf reward learning algorithm from RL for joint data manipulation learning and model …
Portland State University（波特兰州立大学）；Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences（中国科学院大学）；Dalian Maritime University（大连海事大学）；Jilin University（吉林大学）
The inverse probability weighting (IPW) is broadly utilized to address missing data problems including causal inference but may suffer from large variances and biases due to propensity score model misspecification. To solve these problems, I propose an estimation method called the navigated weighting (NAWT), which utilizes estimating equations suitable for a specific pre-specified parameter of interest (e.g., the average treatment effects on the treated). Since these pre-specified parameters determine the relative importance of each unit as a function of propensity scores, the NAWT prioritizes…
We study a nonparametric approach to Bayesian computation via feature means, where the expectation of prior features is updated to yield expected kernel posterior features, based on regression from learned neural net or kernel features of the observations. All quantities involved in the Bayesian update are learned from observed data, making the method entirely model-free. The resulting algorithm is a novel instance of a kernel Bayes' rule (KBR), based on importance weighting. This results in superior numerical stability to the original approach to KBR, which requires operator inversion. We sho…
Importance weighting is a classic technique to handle distribution shifts. However, prior work has presented strong empirical and theoretical evidence demonstrating that importance weights can have little to no effect on overparameterized neural networks. Is importance weighting truly incompatible with the training of overparameterized neural networks? Our paper answers this in the negative. We show that importance weighting fails not because of the overparameterization, but instead, as a result of using exponentially-tailed losses like the logistic or cross-entropy loss. As a remedy, we show …
College of Information and Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校信息与计算机科学学院）；Department of Computer Science, Mount Holyoke College（曼荷莲学院计算机科学系）
Recent work used importance sampling ideas for better variational bounds on likelihoods. We clarify the applicability of these ideas to pure probabilistic inference, by showing the resulting Importance Weighted Variational Inference (IWVI) technique is an instance of augmented variational inference, thus identifying the looseness in previous work. Experiments confirm IWVI's practicality for probabilistic inference. As a second contribution, we investigate inference with elliptical distributions, which improves accuracy in low dimensions, and convergence in high dimensions.
A Short Survey on Importance Weighting for Machine Learning
The University of Melbourne（墨尔本大学）；School of Mathematics and Statistics（数学与统计学院）；The Institute of Statistical Mathematics（统计数学研究所）；RIKEN（理化学研究所）；Center for Advanced Intelligence Project（先进智能项目中心）
This paper investigates when the importance weighting (IW) correction is needed to address covariate shift, a common situation in supervised learning where the input distributions of training and test data differ. Classic results show that the IW correction is needed when the model is parametric and misspecified. In contrast, recent results indicate that the IW correction may not be necessary when the model is nonparametric and well-specified. We examine the missing case in the literature where the model is nonparametric and misspecified, and show that the IW correction is needed for obtaining…
Walmart Labs（沃尔玛实验室）；University of California, Berkeley（加州大学伯克利分校）；Instacart
The recent paper by Byrd & Lipton (2019), based on empirical observations, raises a major concern on the impact of importance weighting for the over-parameterized deep learning models. They observe that as long as the model can separate the training data, the impact of importance weighting diminishes as the training proceeds. Nevertheless, there lacks a rigorous characterization of this phenomenon. In this paper, we provide formal characterizations and theoretical justifications on the role of importance weighting with respect to the implicit bias of gradient descent and margin-based learning …
Estimating marginal treatment effects from observational studies and indirect treatment comparisons: When are standardization-based methods preferable to those based on propensity score weighting?
Biased sampling and missing data complicates statistical problems ranging from causal inference to reinforcement learning. We often correct for biased sampling of summary statistics with matching methods and importance weighting. In this paper, we study nearest neighbor matching (NNM), which makes estimates of population quantities from biased samples by substituting unobserved variables with their nearest neighbors in the biased sample. We show that NNM is $L_2$-consistent in the absence of smoothness and boundedness assumptions in finite dimensions. We discuss applications of NNM, outline th…
Many contemporary machine learning models require extensive tuning of hyperparameters to perform well. A variety of methods, such as Bayesian optimization, have been developed to automate and expedite this process. However, tuning remains extremely costly as it typically requires repeatedly fully training models. We propose to accelerate the Bayesian optimization approach to hyperparameter tuning for neural networks by taking into account the relative amount of information contributed by each training example. To do so, we leverage importance sampling (IS); this significantly increases the qua…
Under distribution shift (DS) where the training data distribution differs from the test one, a powerful technique is importance weighting (IW) which handles DS in two separate steps: weight estimation (WE) estimates the test-over-training density ratio and weighted classification (WC) trains the classifier from weighted training data. However, IW cannot work well on complex data, since WE is incompatible with deep learning. In this paper, we rethink IW and theoretically show it suffers from a circular dependency: we need not only WE for WC, but also WC for WE where a trained deep classifier i…
A learned generative model often produces biased statistics relative to the underlying data distribution. A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions. When the likelihood ratio is unknown, it can be estimated by training a probabilistic classifier to distinguish samples from the two distributions. We employ this likelihood-free importance weighting method to correct for the bias in generative models. We find that this technique consistently improves standard goodness-of-fi…
Latent-Space Importance Weighting under Covariate Shift
Wuhan University（武汉大学）；The Hong Kong University of Science and Technology（香港科技大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（港深创新研究院）
Low Variance Off-policy Evaluation with State-based Importance Sampling
Agency for Science, Technology and Research（新加坡科技研究局）；Manning College of Information and Computer Sciences（曼宁信息与计算机科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Manufacture Française des Pneumatiques Michelin（法国米其林轮胎制造公司）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；ENS Paris-Saclay（巴黎萨克雷高等师范学院）
Bias in datasets can be very detrimental for appropriate statistical estimation. In response to this problem, importance weighting methods have been developed to match any biased distribution to its corresponding target unbiased distribution. The seminal Kernel Mean Matching (KMM) method is, nowadays, still considered as state of the art in this research field. However, one of the main drawbacks of this method is the computational burden for large datasets. Building on previous works by Huang et al. (2007) and de Mathelin et al. (2021), we derive a novel importance weighting algorithm which sc…
Feature selection methods are widely used in order to solve the 'curse of dimensionality' problem. Many proposed feature selection frameworks, treat all data points equally; neglecting their different representation power and importance. In this paper, we propose an unsupervised hypergraph feature selection method via a novel point-weighting framework and low-rank representation that captures the importance of different data points. We introduce a novel soft hypergraph with low complexity to model data. Then, we formulate the feature selection as an optimization problem to preserve local relat…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Mount Holyoke College（曼荷莲学院）
Recent research has seen several advances relevant to black-box VI, but the current state of automatic posterior inference is unclear. One such advance is the use of normalizing flows to define flexible posterior densities for deep latent variable models. Another direction is the integration of Monte-Carlo methods to serve two purposes; first, to obtain tighter variational objectives for optimization, and second, to define enriched variational families through sampling. However, both flows and variational Monte-Carlo methods remain relatively unexplored for black-box VI. Moreover, on a pragmat…
Netherlands eScience Center（荷兰电子科学中心）；Delft University of Technology（代尔夫特理工大学）；University of Copenhagen（哥本哈根大学）
Importance-weighting is a popular and well-researched technique for dealing with sample selection bias and covariate shift. It has desirable characteristics such as unbiasedness, consistency and low computational complexity. However, weighting can have a detrimental effect on an estimator as well. In this work, we empirically show that the sampling distribution of an importance-weighted estimator can be skewed. For sample selection bias settings, and for small sample sizes, the importance-weighted risk estimator produces overestimates for datasets in the body of the sampling distribution, i.e.…
In many learning problems, the training and testing data follow different distributions and a particularly common situation is the \textit{covariate shift}. To correct for sampling biases, most approaches, including the popular kernel mean matching (KMM), focus on estimating the importance weights between the two distributions. Reweighting-based methods, however, are exposed to high variance when the distributional discrepancy is large and the weights are poorly estimated. On the other hand, the alternate approach of using nonparametric regression (NR) incurs high bias when the training size i…
LIPN（巴黎第十三大学计算机科学实验室）；Université Sorbonne Paris Nord（索邦巴黎北大学）；INRIA Paris（法国国家信息与自动化研究所巴黎分部）
Even though Variational Autoencoders (VAEs) are widely used for semi-supervised learning, the reason why they work remains unclear. In fact, the addition of the unsupervised objective is most often vaguely described as a regularization. The strength of this regularization is controlled by down-weighting the objective on the unlabeled part of the training set. Through an analysis of the objective of semi-supervised VAEs, we observe that they use the posterior of the learned generative model to guide the inference model in learning the partially observed latent variable. We show that given this …
Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting
TUM School of Computation, Information and Technology（慕尼黑技术大学计算、信息与技术学院）；Technical University of Munich（慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Department of Computing, Imperial College London（伦敦帝国学院计算机系）
Harbin Institute of Technology（哈尔滨工业大学）；Southern University of Science and Technology（南方科技大学）；Peng Cheng Laboratory（鹏城实验室）
Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source scenario. In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains. In this article, we study the multisource HDA problem and propose a conditional weighting adversarial network (CWAN) to address it. The proposed CWAN adversarially learns a feature transformer, a label classifier, and a domain discriminator. To quantify the importance of diffe…
Tianjin University（天津大学）；Hong Kong University of Science and Technology（香港科技大学）；Tencent AI Lab（腾讯人工智能实验室）
Subpopulation shift widely exists in many real-world machine learning applications, referring to the training and test distributions containing the same subpopulation groups but varying in subpopulation frequencies. Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset. However, some recent studies have recognized that most of these approaches fail to improve the performance over empirical risk minimization especially when applied to over-parameterized neural networks. In this work…
Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
The Institute of Statistical Mathematics（统计数学研究所）；University of Bristol（布里斯托大学）；RIKEN Center for Advanced Intelligence Project（RIKEN高级智能项目中心）；The University of Tokyo（东京大学）
It is important to forecast dam inflow for flood damage mitigation. The hydrograph provides critical information such as the start time, peak level, and volume. Particularly, dam management requires a 6-h lead time of the dam inflow forecast based on a future hydrograph. The authors propose novel target inflow weights to create an ocean feature vector extracted from the analyzed images of the sea surface. We extracted 4,096 elements of the dimension vector in the fc6 layer of the pre-trained VGG16 network. Subsequently, we reduced it to three dimensions of t-SNE. Furthermore, we created the pr…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；ASAPP, Inc.（ASAPP公司）；Amazon, Inc.（亚马逊公司）；CognitiveScale（CognitiveScale公司）
Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution. However, often we do not have direct access to our target distribution - our data may be subject to sample selection bias, or may be from a different but related distribution. We present methods based on importance weighting that can estimate the loss with respect to a target distribution, even if we cannot access that distribution directly, in a variety of settings. These estimators, which differentially weight the contribution of data to the loss func…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Harvard University (SEAS)（哈佛大学工程与应用科学学院）；Lunenfeld Tanenbaum Research Institute（卢嫩菲尔德-塔南鲍姆研究所）；The Hospital for Sick Children（病童医院）
Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature. We propose FIT, a framework that evaluates the importance of observations for a multivariate time-series black-box model by quantifying the shift in the predictive distribution over time. FIT defines the importance of an observation based on its contribution to the distributional shift under a KL-divergence that contrasts the predictive distribution against a counterfactual where the rest of the features are unobserved. We also demonstrat…
The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximately factorial, and that its parameters can be approximated with nonlinear regression from the observations. As we show empirically, the VAE objective can lead to overly simplified representations which fail to use the network's entire modeling capacity. We present…
Machine learning models are often deployed in different settings than they were trained and validated on, posing a challenge to practitioners who wish to predict how well the deployed model will perform on a target distribution. If an unlabeled sample from the target distribution is available, along with a labeled sample from a possibly different source distribution, standard approaches such as importance weighting can be applied to estimate performance on the target. However, importance weighting struggles when the source and target distributions have non-overlapping support or are high-dimen…
QGAPHEnsemble : Combining Hybrid QLSTM Network Ensemble via Adaptive Weighting for Short Term Weather Forecasting
Georgia Institute of Technology（佐治亚理工学院）；Indian Institute of Engineering Science and Technology, Shibpur（印度工程科学技术学院（希布普尔））；IIT Roorkee（鲁基印度理工学院）；National Institute of Technology, Rourkela（罗尔克拉国家理工学院）；National Institute of Technology Karnataka（卡纳塔克邦国家理工学院）；Jadavpur University（贾达沃普尔大学）
