In this work, we present a variety of novel information-theoretic generalization bounds for learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the setting of the "conditional mutual information" framework. Our development exploits projecting the loss pair (obtained from a training instance and a testing instance) down to a single number and correlating loss values with a Rademacher sequence (and its shifted variants). The presented bounds include square-root bounds, fast-rate bounds, including those based on variance and sharpness, and bounds for interpolating algorithms etc. We show theoretically or empirically that these bounds are tighter than all information-theoretic bounds known to date on the same supersample setting.
Chalmers University of Technology（查尔姆斯理工大学）；Kings College London（伦敦国王学院）
Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks. This paper presents an information-theoretic bound on the generalization performance of any given meta-learner, which builds on the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020). In the proposed extension to meta-learning, the CMI bound involves a training \textit{meta-supersample} obtained by first sampling $2N$ independent tasks from the task environment, and then drawing $2M$ indepe…
Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
Department of Electrical and Electronic Engineering, Imperial College London（帝国理工学院伦敦分校电子与电气工程系）；Department of Information Engineering, The Chinese University of Hong Kong（香港中文大学信息工程系）
Generalization Bounds via Conditional $f$-Information
School of Computer Science and Technology（计算机科学与技术学院）；Tongji University（同济大学）；School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）；University of Ottawa（渥太华大学）
University of Toronto（多伦多大学）；Vector Institute（矢量研究所）；Element AI（Element AI公司）
The information-theoretic framework of Russo and J. Zou (2016) and Xu and Raginsky (2017) provides bounds on the generalization error of a learning algorithm in terms of the mutual information between the algorithm's output and the training sample. In this work, we study the proposal, by Steinke and Zakynthinou (2020), to reason about the generalization error of a learning algorithm by introducing a super sample that contains the training sample as a random subset and computing mutual information conditional on the super sample. We first show that these new bounds based on the conditional mutu…
Graph Convolutional Networks (GCNs) have achieved impressive empirical advancement across a wide variety of semi-supervised node classification tasks. Despite their great success, training GCNs on large graphs suffers from computational and memory issues. A potential path to circumvent these obstacles is sampling-based methods, where at each layer a subset of nodes is sampled. Although recent studies have empirically demonstrated the effectiveness of sampling-based methods, these works lack theoretical convergence guarantees under realistic settings and cannot fully leverage the information of…
We study the problem of differentially private (DP) matrix completion under user-level privacy. We design a joint differentially private variant of the popular Alternating-Least-Squares (ALS) method that achieves: i) (nearly) optimal sample complexity for matrix completion (in terms of number of items, users), and ii) the best known privacy/utility trade-off both theoretically, as well as on benchmark data sets. In particular, we provide the first global convergence analysis of ALS with noise introduced to ensure DP, and show that, in comparison to the best known alternative (the Private Frank…
City University of Hong Kong（香港城市大学）；Microsoft Research（微软研究院）；TU Berlin（柏林工业大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Humboldt University of Berlin（柏林洪堡大学）
This paper studies the generalization performance of multi-class classification algorithms, for which we obtain, for the first time, a data-dependent generalization error bound with a logarithmic dependence on the class size, substantially improving the state-of-the-art linear dependence in the existing data-dependent generalization analysis. The theoretical analysis motivates us to introduce a new multi-class classification machine based on $\ell_p$-norm regularization, where the parameter $p$ controls the complexity of the corresponding bounds. We derive an efficient optimization algorithm b…
This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a duality between generalisation bounds based on the regularity of the loss function, and their chained counterparts, which can be obtained by lifting the regularity assumption from the loss onto its gradient. This allows us to re-derive the chaining mutual information bound from the literature, and to obtain novel chained information-theoretic generalisation bounds, based on the Wa…
Convolutional neural networks (CNNs) have achieved breakthrough performances in a wide range of applications including image classification, semantic segmentation, and object detection. Previous research on characterizing the generalization ability of neural networks mostly focuses on fully connected neural networks (FNNs), regarding CNNs as a special case of FNNs without taking into account the special structure of convolutional layers. In this work, we propose a tighter generalization bound for CNNs by exploiting the sparse and permutation structure of its weight matrices. As the generalizat…
We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding of both the conventional learning-to-learn framework and the modern model-agnostic meta-learning (MAML) algorithms. Moreover, we provide a data-dependent generalization bound for a stochastic variant of MAML, which is non-vacuous for deep few-shot learning. As compared to previous bounds that depend on the square norm of gradients, empirical validations on both simulated data and a well-known few-shot benchmark show that our boun…
Communication overhead is one of the key challenges that hinders the scalability of distributed optimization algorithms. In this paper, we study local distributed SGD, where data is partitioned among computation nodes, and the computation nodes perform local updates with periodically exchanging the model among the workers to perform averaging. While local SGD is empirically shown to provide promising results, a theoretical understanding of its performance remains open. We strengthen convergence analysis for local SGD, and show that local SGD can be far less expensive and applied far more gener…
Paris Research Center, Huawei Technologies France（华为技术法国巴黎研究中心）；Université Paris-Est（巴黎东大学）
In this paper, we use tools from rate-distortion theory to establish new upper bounds on the generalization error of statistical distributed learning algorithms. Specifically, there are $K$ clients whose individually chosen models are aggregated by a central server. The bounds depend on the compressibility of each client's algorithm while keeping other clients' algorithms un-compressed, and leverage the fact that small changes in each local model change the aggregated model by a factor of only $1/K$. Adopting a recently proposed approach by Sefidgaran et al., and extending it suitably to the d…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning. An interesting theoretical finding is that the larger the diversity of each local estimate is, the tighter the risk bound is. This theoretical analysis motivates us to devise an effective maxdiversity distributed learning algorithm (MDD). Experimental results show that MDD can outperform the existing divide-andconquer methods but with a bit more time. Theoret…
Harvard University（哈佛大学）；Universidad Nacional Autónoma de México（墨西哥国立自治大学）
We investigate the framework of privacy amplification by iteration, recently proposed by Feldman et al., from an information-theoretic lens. We demonstrate that differential privacy guarantees of iterative mappings can be determined by a direct application of contraction coefficients derived from strong data processing inequalities for $f$-divergences. In particular, by generalizing the Dobrushin's contraction coefficient for total variation distance to an $f$-divergence known as $E_γ$-divergence, we derive tighter bounds on the differential privacy parameters of the projected noisy stochastic…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Massachusetts Institute of Technology（麻省理工学院）；University at Buffalo, The State University of New York（纽约州立大学布法罗分校）
An information-theoretic upper bound on the generalization error of supervised learning algorithms is derived. The bound is constructed in terms of the mutual information between each individual training sample and the output of the learning algorithm. The bound is derived under more general conditions on the loss function than in existing studies; nevertheless, it provides a tighter characterization of the generalization error. Examples of learning algorithms are provided to demonstrate the the tightness of the bound, and to show that it has a broad range of applicability. Application to nois…
Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the MI in DNNs, thus most previous works have to relax the MI bound, which in turn weakens the information theoretic explanation for generalization. To address the limitation, this paper introduces a probabilistic representation of DNNs for accurately estimating the MI. Leveraging the proposed MI estimator, we validate the information theoretic explanation for generalization, and derive a tighter generalization bound th…
We present a new family of information-theoretic generalization bounds, in which the training loss and the population loss are compared through a jointly convex function. This function is upper-bounded in terms of the disintegrated, samplewise, evaluated conditional mutual information (CMI), an information measure that depends on the losses incurred by the selected hypothesis, rather than on the hypothesis itself, as is common in probably approximately correct (PAC)-Bayesian results. We demonstrate the generality of this framework by recovering and extending previously known information-theore…
Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key performance measure for meta-learning is the meta-generalization gap, that is, the difference between the average loss measured on the meta-training data and on a new, randomly selected task. This paper presents novel information-theoretic upper bounds on the meta-generalization gap. Two broad classes of meta-learning algorithms are considered that uses either sepa…
Generalization Bounds for Transformer Channel Decoders
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Pengcheng Laboratory（鹏城实验室）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；University Town of Shenzhen, Nanshan District, Shenzhen（深圳大学城，南山区，深圳）
Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different distributions (denoted as $μ$ and $μ'$, respectively). In this work, we give an information-theoretic analysis on the generalization error and the excess risk of transfer learning algorithms, following a line of work initiated by Russo and Zhou. Our results suggest, perhaps as expected, that the Kullback-Leibler (KL) divergence $D(mu||mu')$ plays an important role in characterizing the generalization error in the settings of domain adaptation. Spe…
Generalization error bounds are critical to understanding the performance of machine learning models. In this work, we propose a new information-theoretic based generalization error upper bound applicable to supervised learning scenarios. We show that our general bound can specialize in various previous bounds. We also show that our general bound can be specialized under some conditions to a new bound involving the Jensen-Shannon information between a random variable modelling the set of training samples and another random variable modelling the hypothesis. We also prove that our bound can be …
In this paper, we propose a novel {\em $e$-exponentiated} transformation, $0 \le e<1$, for loss functions. When the transformation is applied to a convex loss function, the transformed loss function become more robust to outliers. Using a novel generalization error bound, we have theoretically shown that the transformed loss function has a tighter bound for datasets corrupted by outliers. Our empirical observation shows that the accuracy obtained using the transformed loss function can be significantly better than the same obtained using the original loss function and comparable to that obtain…
Koopman-based generalization bound: New aspect for full-rank weights
NTT Corporation（NTT公司）；Center for Advanced Intelligence Project, RIKEN（理化学研究所先进智能项目中心）；Center for Data Science, Ehime University（爱媛大学数据科学中心）；A*STAR Centre for Frontier AI and Research（新加坡科技研究局前沿人工智能与研究中心）；Graduate School of Information Science and Technology, The University of Tokyo（东京大学情报理工学研究科）
Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning
School of Mathematics and Statistics（数学与统计学学院）；Guangxi Normal University（广西师范大学）；School of Mathematics（数学学院）；Hohai University（河海大学）；College of Marine Life Sciences（海洋生命科学学院）；Ocean University of China（中国海洋大学）；State Key Laboratory of Mathematical Sciences（数学科学国家重点实验室）；Academy of Mathematics and Systems Science（数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）
We address two fundamental questions about graph neural networks (GNNs). First, we prove that several important graph properties cannot be computed by GNNs that rely entirely on local information. Such GNNs include the standard message passing models, and more powerful spatial variants that exploit local graph structure (e.g., via relative orientation of messages, or local port ordering) to distinguish neighbors of each node. Our treatment includes a novel graph-theoretic formalism. Second, we provide the first data dependent generalization bounds for message passing GNNs. This analysis explic…
We consider the problem of ranking a set of items from pairwise comparisons in the presence of features associated with the items. Recent works have established that $O(n\log(n))$ samples are needed to rank well when there is no feature information present. However, this might be sub-optimal in the presence of associated features. We introduce a new probabilistic preference model called feature-Bradley-Terry-Luce (f-BTL) model that generalizes the standard BTL model to incorporate feature information. We present a new least squares based algorithm called fBTL-LS which we show requires much les…
Recent theoretical works based on the neural tangent kernel (NTK) have shed light on the optimization and generalization of over-parameterized networks, and partially bridge the gap between their practical success and classical learning theory. Especially, using the NTK-based approach, the following three representative results were obtained: (1) A training error bound was derived to show that networks can fit any finite training sample perfectly by reflecting a tighter characterization of training speed depending on the data complexity. (2) A generalization error bound invariant of network si…
Information-Theoretic Generalization Bounds of Replay-based Continual Learning
School of Computer Science and Technology, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院）；Department of Oncology, University of Cambridge（剑桥大学肿瘤学系）；China Telecom, China（中国电信）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
ITBoost: Information-Theoretic Trust for Robust Boosting
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Software Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada（软件工程系，安达卢西亚数据科学与计算智能研究所（DaSCI），格拉纳达大学）；College of Information Science and Technology, Beijing University of Chemical Technology（信息科学与技术学院，北京化工大学）
The $\ell_0$-constrained empirical risk minimization ($\ell_0$-ERM) is a promising tool for high-dimensional statistical estimation. The existing analysis of $\ell_0$-ERM estimator is mostly on parameter estimation and support recovery consistency. From the perspective of statistical learning, another fundamental question is how well the $\ell_0$-ERM estimator would perform on unseen samples. The answer to this question is important for understanding the learnability of such a non-convex (and also NP-hard) M-estimator but still relatively under explored. In this paper, we investigate this prob…
University of Iowa（爱荷华大学）；University of California, Davis（加利福尼亚大学戴维斯分校）；Red Trading Group, LLC（3Red交易集团有限责任公司）
Donald Trump was lagging behind in nearly all opinion polls leading up to the 2016 US presidential election, but he surprisingly won the election. This raises the following important questions: 1) why most opinion polls were not accurate in 2016? and 2) how to improve the accuracies of opinion polls? In this paper, we study the inaccuracies of opinion polls in the 2016 election through the lens of information theory. We first propose a general framework of parameter estimation, called clean sensing (polling), which performs optimal parameter estimation with sensing cost constraints, from heter…
University of Oxford（牛津大学）；University of British Columbia（英属哥伦比亚大学）
We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter ELBOs are better variational objectives for simultaneous model learning and inference amortization schemes. Based on our insights, we introduce three new algorithms: the partially importance weighted auto-encoder (PIWAE), the multiply importance weighted auto-encoder (MIWAE), and the combination impo…
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
The expressiveness of deep neural network (DNN) is a perspective to understandthe surprising performance of DNN. The number of linear regions, i.e. pieces thata piece-wise-linear function represented by a DNN, is generally used to measurethe expressiveness. And the upper bound of regions number partitioned by a rec-tifier network, instead of the number itself, is a more practical measurement ofexpressiveness of a rectifier DNN. In this work, we propose a new and tighter up-per bound of regions number. Inspired by the proof of this upper bound and theframework of matrix computation in Hinz & Va…
The CUR matrix decomposition is an important extension of Nyström approximation to a general matrix. It approximates any data matrix in terms of a small number of its columns and rows. In this paper we propose a novel randomized CUR algorithm with an expected relative-error bound. The proposed algorithm has the advantages over the existing relative-error CUR algorithms that it possesses tighter theoretical bound and lower time complexity, and that it can avoid maintaining the whole data matrix in main memory. Finally, experiments on several real-world datasets demonstrate significant improveme…
University of Oxford（牛津大学）；Tsinghua University（清华大学）
In large-scale classification problems, the data set always be faced with frequent updates when a part of the data is added to or removed from the original data set. In this case, conventional incremental learning, which updates an existing classifier by explicitly modeling the data modification, is more efficient than retraining a new classifier from scratch. However, sometimes, we are more interested in determining whether we should update the classifier or performing some sensitivity analysis tasks. To deal with these such tasks, we propose an algorithm to make rational inferences about the…
This report explains, implements and extends the works presented in "Tighter Variational Bounds are Not Necessarily Better" (T Rainforth et al., 2018). We provide theoretical and empirical evidence that increasing the number of importance samples $K$ in the importance weighted autoencoder (IWAE) (Burda et al., 2016) degrades the signal-to-noise ratio (SNR) of the gradient estimator in the inference network and thereby affecting the full learning process. In other words, even though increasing $K$ decreases the standard deviation of the gradients, it also reduces the magnitude of the true gradi…
In statistical inference problems, we wish to obtain lower bounds on the minimax risk, that is to bound the performance of any possible estimator. A standard technique to obtain risk lower bounds involves the use of Fano's inequality. In an information-theoretic setting, it is known that Fano's inequality typically does not give a sharp converse result (error lower bound) for channel coding problems. Moreover, recent work has shown that an argument based on binary hypothesis testing gives tighter results. We adapt this technique to the statistical setting, and argue that Fano's inequality can …
Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
Bosch Center for Artificial Intelligence（博世人工智能中心）；Technische Universität Darmstadt（达姆施塔特工业大学）；University of Southern Denmark（南丹麦大学）；Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI)（德国人工智能研究中心）
INRIA Lille - Nord Europe（法国国立信息学及其应用研究院里尔-北欧研究中心）；Renault Group（雷诺集团）
We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies - i.e. sequences of actions - and under budget constraint. In this setting, the Open-Loop Optimistic Planning (OLOP) algorithm enjoys good theoretical guarantees but is overly conservative in practice, as we show in numerical experiments. We propose a modified version of the algorithm with tighter upper-confidence bounds, KLOLOP, that leads to better practical performances while retaining the sample complexity bound. Finally, we propose an effic…
