PyTorchKR Papers

최신 논문

총 822편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2212.02264

Bagging is an Optimal PAC Learner

Determining the optimal sample complexity of PAC learning in the realizable setting was a central open problem in learning theory for decades. Finally, the seminal work by Hanneke (2016) gave an algorithm with a provably optimal sample complexity. His algorithm is based on a careful and structured sub-sampling of the training data and then returning a majority vote among hypotheses trained on each of the sub-samples. While being a very exciting theoretical result, it has not had much impact in practice, in part due to inefficiency, since it constructs a polynomial number of sub-samples of the training data, each of linear size. In this work, we prove the surprising result that the practical and classic heuristic bagging (a.k.a. bootstrap aggregation), due to Breiman (1996), is in fact also an optimal PAC learner. Bagging pre-dates Hanneke's algorithm by twenty years and is taught in most undergraduate machine learning courses. Moreover, we show that it only requires a logarithmic number of sub-samples to reach optimality.

arXiv:2212.00802

An Introduction to Kernel and Operator Learning Methods for Homogenization by Self-consistent Clustering Analysis

Recent advances in operator learning theory have improved our knowledge about learning maps between infinite dimensional spaces. However, for large-scale engineering problems such as concurrent multiscale simulation for mechanical properties, the training cost for the current operator learning methods is very high. The article presents a thorough analysis on the mathematical underpinnings of the operator learning paradigm and proposes a kernel learning method that maps between function spaces. We first provide a survey of modern kernel and operator learning theory, as well as discuss recent results and open problems. From there, the article presents an algorithm to how we can analytically approximate the piecewise constant functions on R for operator learning. This implies the potential feasibility of success of neural operators on clustered functions. Finally, a k-means clustered domain on the basis of a mechanistic response is considered and the Lippmann-Schwinger equation for micro-mechanical homogenization is solved. The article briefly discusses the mathematics of previous kernel learning methods and some preliminary results with those methods. The proposed kernel operator learning method uses graph kernel networks to come up with a mechanistic reduced order method for multiscale homogenization.

arXiv:2211.16229

Triadic Temporal Exponential Random Graph Models (TTERGM)

Temporal exponential random graph models (TERGM) are powerful statistical models that can be used to infer the temporal pattern of edge formation and elimination in complex networks (e.g., social networks). TERGMs can also be used in a generative capacity to predict longitudinal time series data in these evolving graphs. However, parameter estimation within this framework fails to capture many real-world properties of social networks, including: triadic relationships, small world characteristics, and social learning theories which could be used to constrain the probabilistic estimation of dyadic covariates. Here, we propose triadic temporal exponential random graph models (TTERGM) to fill this void, which includes these hierarchical network relationships within the graph model. We represent social network learning theory as an additional probability distribution that optimizes Markov chains in the graph vector space. The new parameters are then approximated via Monte Carlo maximum likelihood estimation. We show that our TTERGM model achieves improved fidelity and more accurate predictions compared to several benchmark methods on GitHub network data.

arXiv:2211.13312

A Moment-Matching Approach to Testable Learning and a New Characterization of Rademacher Complexity

A remarkable recent paper by Rubinfeld and Vasilyan (2022) initiated the study of \emph{testable learning}, where the goal is to replace hard-to-verify distributional assumptions (such as Gaussianity) with efficiently testable ones and to require that the learner succeed whenever the unknown distribution passes the corresponding test. In this model, they gave an efficient algorithm for learning halfspaces under testable assumptions that are provably satisfied by Gaussians. In this paper we give a powerful new approach for developing algorithms for testable learning using tools from moment matching and metric distances in probability. We obtain efficient testable learners for any concept class that admits low-degree \emph{sandwiching polynomials}, capturing most important examples for which we have ordinary agnostic learners. We recover the results of Rubinfeld and Vasilyan as a corollary of our techniques while achieving improved, near-optimal sample complexity bounds for a broad range of concept classes and distributions. Surprisingly, we show that the information-theoretic sample complexity of testable learning is tightly characterized by the Rademacher complexity of the concept class, one of the most well-studied measures in statistical learning theory. In particular, uniform convergence is necessary and sufficient for testable learning. This leads to a fundamental separation from (ordinary) distribution-specific agnostic learning, where uniform convergence is sufficient but not necessary.

arXiv:2211.09101

Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes

In many learning theory problems, a central role is played by a hypothesis class: we might assume that the data is labeled according to a hypothesis in the class (usually referred to as the realizable setting), or we might evaluate the learned model by comparing it with the best hypothesis in the class (the agnostic setting). Taking a step beyond these classic setups that involve only a single hypothesis class, we introduce comparative learning as a combination of the realizable and agnostic settings in PAC learning: given two binary hypothesis classes $S$ and $B$, we assume that the data is labeled according to a hypothesis in the source class $S$ and require the learned model to achieve an accuracy comparable to the best hypothesis in the benchmark class $B$. Even when both $S$ and $B$ have infinite VC dimensions, comparative learning can still have a small sample complexity. We show that the sample complexity of comparative learning is characterized by the mutual VC dimension $\mathsf{VC}(S,B)$ which we define to be the maximum size of a subset shattered by both $S$ and $B$. We also show a similar result in the online setting, where we give a regret characterization in terms of the mutual Littlestone dimension $\mathsf{Ldim}(S,B)$. These results also hold for partial hypotheses. We additionally show that the insights necessary to characterize the sample complexity of comparative learning can be applied to characterize the sample complexity of realizable multiaccuracy and multicalibration using the mutual fat-shattering dimension, an analogue of the mutual VC dimension for real-valued hypotheses. This not only solves an open problem proposed by Hu, Peale, Reingold (2022), but also leads to independently interesting results extending classic ones about regression, boosting, and covering number to our two-hypothesis-class setting.

arXiv:2211.06387

Õptimal Differentially Private Learning of Thresholds and Quasi-Concave Optimization

The problem of learning threshold functions is a fundamental one in machine learning. Classical learning theory implies sample complexity of $O(\xi^{-1} \log(1/\beta))$ (for generalization error $\xi$ with confidence $1-\beta$). The private version of the problem, however, is more challenging and in particular, the sample complexity must depend on the size $|X|$ of the domain. Progress on quantifying this dependence, via lower and upper bounds, was made in a line of works over the past decade. In this paper, we finally close the gap for approximate-DP and provide a nearly tight upper bound of $\tilde{O}(\log^* |X|)$, which matches a lower bound by Alon et al (that applies even with improper learning) and improves over a prior upper bound of $\tilde{O}((\log^* |X|)^{1.5})$ by Kaplan et al. We also provide matching upper and lower bounds of $\tilde{\Theta}(2^{\log^*|X|})$ for the additive error of private quasi-concave optimization (a related and more general problem). Our improvement is achieved via the novel Reorder-Slice-Compute paradigm for private data analysis which we believe will have further applications.

arXiv:2211.06182

An introduction to computational complexity and statistical learning theory applied to nuclear models

The fact that we can build models from data, and therefore refine our models with more data from experiments, is usually given for granted in scientific inquiry. However, how much information can we extract, and how precise can we expect our learned model to be, if we have only a finite amount of data at our disposal? Nuclear physics demands an high degree of precision from models that are inferred from the limited number of nuclei that can be possibly made in the laboratories. In manuscript I will introduce some concepts of computational science, such as statistical theory of learning and Hamiltonian complexity, and use them to contextualise the results concerning the amount of data necessary to extrapolate a mass model to a given precision.

arXiv:2211.04956

A Characterization of List Learnability

A classical result in learning theory shows the equivalence of PAC learnability of binary hypothesis classes and the finiteness of VC dimension. Extending this to the multiclass setting was an open problem, which was settled in a recent breakthrough result characterizing multiclass PAC learnability via the DS dimension introduced earlier by Daniely and Shalev-Shwartz. In this work we consider list PAC learning where the goal is to output a list of $k$ predictions. List learning algorithms have been developed in several settings before and indeed, list learning played an important role in the recent characterization of multiclass learnability. In this work we ask: when is it possible to $k$-list learn a hypothesis class? We completely characterize $k$-list learnability in terms of a generalization of DS dimension that we call the $k$-DS dimension. Generalizing the recent characterization of multiclass learnability, we show that a hypothesis class is $k$-list learnable if and only if the $k$-DS dimension is finite.

arXiv:2210.15435

Grokking phase transitions in learning local rules with gradient descent

We discuss two solvable grokking (generalisation beyond overfitting) models in a rule learning scenario. We show that grokking is a phase transition and find exact analytic expressions for the critical exponents, grokking probability, and grokking time distribution. Further, we introduce a tensor-network map that connects the proposed grokking setup with the standard (perceptron) statistical learning theory and show that grokking is a consequence of the locality of the teacher model. As an example, we analyse the cellular automata learning task, numerically determine the critical exponent and the grokking time distributions and compare them with the prediction of the proposed grokking model. Finally, we numerically analyse the connection between structure formation and grokking.

arXiv:2210.14707

Is Out-of-Distribution Detection Learnable?

Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms. To study the generalization of OOD detection, in this paper, we investigate the probably approximately correct (PAC) learning theory of OOD detection, which is proposed by researchers as an open problem. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we also offer theoretical supports for several representative OOD detection works based on our OOD theory.

arXiv:2210.12195

Just Mix Once: Worst-group Generalization by Group Interpolation

Advances in deep learning theory have revealed how average generalization relies on superficial patterns in data. The consequences are brittle models with poor performance with shift in group distribution at test time. When group annotation is available, we can use robust optimization tools to tackle the problem. However, identification and annotation are time-consuming, especially on large datasets. A recent line of work leverages self-supervision and oversampling to improve generalization on minority groups without group annotation. We propose to unify and generalize these approaches using a class-conditional variant of mixup tailored for worst-group generalization. Our approach, Just Mix Once (JM1), interpolates samples during learning, augmenting the training distribution with a continuous mixture of groups. JM1 is domain agnostic and computationally efficient, can be used with any level of group annotation, and performs on par or better than the state-of-the-art on worst-group generalization. Additionally, we provide a simple explanation of why JM1 works.

arXiv:2210.13331

Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport

Domain adaptation arises as an important problem in statistical learning theory when the data-generating processes differ between training and test samples, respectively called source and target domains. Recent theoretical advances show that the success of domain adaptation algorithms heavily relies on their ability to minimize the divergence between the probability distributions of the source and target domains. However, minimizing this divergence cannot be done independently of the minimization of other key ingredients such as the source risk or the combined error of the ideal joint hypothesis. The trade-off between these terms is often ensured by algorithmic solutions that remain implicit and not directly reflected by the theoretical guarantees. To get to the bottom of this issue, we propose in this paper a new theoretical framework for domain adaptation through hierarchical optimal transport. This framework provides more explicit generalization bounds and allows us to consider the natural hierarchical organization of samples in both domains into classes or clusters. Additionally, we provide a new divergence measure between the source and target domains called Hierarchical Wasserstein distance that indicates under mild assumptions, which structures have to be aligned to lead to a successful adaptation.

arXiv:2210.12361

MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images

The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that use a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesions contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results.

arXiv:2210.09435

Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy

In complex environments, where the human sensory system reaches its limits, our behaviour is strongly driven by our beliefs about the state of the world around us. Accessing others' beliefs, intentions, or mental states in general, could thus allow for more effective social interactions in natural contexts. Yet these variables are not directly observable. Theory of Mind (TOM), the ability to attribute to other agents' beliefs, intentions, or mental states in general, is a crucial feature of human social interaction and has become of interest to the robotics community. Recently, new models that are able to learn TOM have been introduced. In this paper, we show the synergy between learning to predict low-level mental states, such as intentions and goals, and attributing high-level ones, such as beliefs. Assuming that learning of beliefs can take place by observing own decision and beliefs estimation processes in partially observable environments and using a simple feed-forward deep learning model, we show that when learning to predict others' intentions and actions, faster and more accurate predictions can be acquired if beliefs attribution is learnt simultaneously with action and intentions prediction. We show that the learning performance improves even when observing agents with a different decision process and is higher when observing beliefs-driven chunks of behaviour. We propose that our architectural approach can be relevant for the design of future adaptive social robots that should be able to autonomously understand and assist human partners in novel natural environments and tasks.

arXiv:2210.06511

Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness

Recent work has established that the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees in terms of algorithmic stability, VC dimension, and related complexity measures for conventional learning (Harutyunyan et al., 2021, Haghifam et al., 2021). Hence, it provides a unified method for establishing generalization bounds. In meta learning, there has so far been a divide between information-theoretic results and results from classical learning theory. In this work, we take a first step toward bridging this divide. Specifically, we present novel generalization bounds for meta learning in terms of the evaluated CMI (e-CMI). To demonstrate the expressiveness of the e-CMI framework, we apply our bounds to a representation learning setting, with $n$ samples from $\hat n$ tasks parameterized by functions of the form $f_i \circ h$. Here, each $f_i \in \mathcal F$ is a task-specific function, and $h \in \mathcal H$ is the shared representation. For this setup, we show that the e-CMI framework yields a bound that scales as $\sqrt{ \mathcal C(\mathcal H)/(n\hat n) + \mathcal C(\mathcal F)/n} $, where $\mathcal C(\cdot)$ denotes a complexity measure of the hypothesis class. This scaling behavior coincides with the one reported in Tripuraneni et al. (2020) using Gaussian complexity.

arXiv:2210.05455

Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes

The sample compressibility of concept classes plays an important role in learning theory, as a sufficient condition for PAC learnability, and more recently as an avenue for robust generalisation in adaptive data analysis. Whether compression schemes of size $O(d)$ must necessarily exist for all classes of VC dimension $d$ is unknown, but conjectured to be true by Warmuth. Recently Chalopin, Chepoi, Moran, and Warmuth (2018) gave a beautiful unlabelled sample compression scheme of size VC dimension for all maximum classes: classes that meet the Sauer-Shelah-Perles Lemma with equality. They also offered a counterexample to compression schemes based on a promising approach known as corner peeling. In this paper we simplify and extend their proof technique to deal with so-called extremal classes of VC dimension $d$ which contain maximum classes of VC dimension $d-1$. A criterion is given which would imply that all extremal classes admit unlabelled compression schemes of size $d$. We also prove that all intersection-closed classes with VC dimension $d$ admit unlabelled compression schemes of size at most $11d$.

arXiv:2210.04817

Do you pay for Privacy in Online learning?

Online learning, in the mistake bound model, is one of the most fundamental concepts in learning theory. Differential privacy, instead, is the most widely used statistical concept of privacy in the machine learning community. It is thus clear that defining learning problems that are online differentially privately learnable is of great interest. In this paper, we pose the question on if the two problems are equivalent from a learning perspective, i.e., is privacy for free in the online learning framework?

arXiv:2209.11628공식 코드 · Papers with Code

A Neural Model for Regular Grammar Induction

Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of regular grammars from positive and negative examples. Our model is fully explainable, its intermediate results are directly interpretable as partial parses, and it can be used to learn arbitrary regular grammars when provided with sufficient data. We find that our method consistently attains high recall and precision scores across a range of tests of varying complexity.

arXiv:2209.08005

Stability and Generalization for Markov Chain Stochastic Gradient Methods

Recently there is a large amount of work devoted to the study of Markov chain stochastic gradient methods (MC-SGMs) which mainly focus on their convergence analysis for solving minimization problems. In this paper, we provide a comprehensive generalization analysis of MC-SGMs for both minimization and minimax problems through the lens of algorithmic stability in the framework of statistical learning theory. For empirical risk minimization (ERM) problems, we establish the optimal excess population risk bounds for both smooth and non-smooth cases by introducing on-average argument stability. For minimax problems, we develop a quantitative connection between on-average argument stability and generalization error which extends the existing results for uniform stability \cite{lei2021stability}. We further develop the first nearly optimal convergence rates for convex-concave problems both in expectation and with high probability, which, combined with our stability results, show that the optimal generalization bounds can be attained for both smooth and non-smooth cases. To the best of our knowledge, this is the first generalization analysis of SGMs when the gradients are sampled from a Markov process.

arXiv:2209.07238

Generalization Properties of NAS under Activation and Skip Connection Search

Neural Architecture Search (NAS) has fostered the automatic discovery of state-of-the-art neural architectures. Despite the progress achieved with NAS, so far there is little attention to theoretical guarantees on NAS. In this work, we study the generalization properties of NAS under a unifying framework enabling (deep) layer skip connection search and activation function search. To this end, we derive the lower (and upper) bounds of the minimum eigenvalue of the Neural Tangent Kernel (NTK) under the (in)finite-width regime using a certain search space including mixed activation functions, fully connected, and residual neural networks. We use the minimum eigenvalue to establish generalization error bounds of NAS in the stochastic gradient descent training. Importantly, we theoretically and experimentally show how the derived results can guide NAS to select the top-performing architectures, even in the case without training, leading to a train-free algorithm based on our theory. Accordingly, our numerical validation shed light on the design of computationally efficient methods for NAS. Our analysis is non-trivial due to the coupling of various architectures and activation functions under the unifying framework and has its own interest in providing the lower bound of the minimum eigenvalue of NTK in deep learning theory.