Clayton Scott

ICML Conference 2025 Conference Paper

Feasible Action Search for Bandit Linear Programs via Thompson Sampling

• Aditya Gangrade
• Aldo Pacchiano
• Clayton Scott
• Venkatesh Saligrama

We study the ’feasible action search’ (FAS) problem for linear bandits, wherein a learner attempts to discover a feasible point for a set of linear constraints $\Phi_* a \ge 0, $ without knowledge of the matrix $\Phi_* \in \mathbb{R}^{m \times d}$. A FAS learner selects a sequence of actions $a_t, $ and uses observations of the form $\Phi_* a_t + \mathrm{noise}$ to either find a point with nearly optimal ’safety margin’, or detect that the constraints are infeasible, where the safety margin of an action measures its (signed) distance from the constraint boundary. While of interest in its own right, the FAS problem also directly addresses a key deficiency in the extant theory of ’safe linear bandits’ (SLBs), by discovering a safe initialisation for low-regret SLB methods. We propose and analyse a novel efficient FAS-learner. Our method, FAST, is based on Thompson Sampling. It applies a coupled random perturbation to an estimate of $\Phi_*, $ and plays a maximin point of a game induced by this perturbed matrix. We prove that FAST stops in $\tilde{O}(d^3/\varepsilon^2 M_*^2)$ steps, and incurs $\tilde{O}(d^3/|M_*|)$ safety costs, to either correctly detect infeasibility, or output a point that is at least $(1-\varepsilon) M_*$-safe, where $M_*$ is the optimal safety margin of $\Phi_*$. Further, instantiating prior SLB methods with the output of FAS yields the first SLB methods that incur $\tilde{O}(\sqrt{d^3 T/M_*^2})$ regret and $O(1)$ risk without a priori knowledge of a safe action. The main technical novelty lies in the extension of Thompson Sampling to this multiobjective setting, for which we both propose a coupled noise design, and provide an analysis that avoids convexity considerations.

TMLR Journal 2025 Journal Article

Label Embedding via Low-Coherence Matrices

• Jianxin Zhang
• Clayton Scott

Label embedding is a framework for multiclass classification problems where each label is represented by a distinct vector of some fixed dimension, and training involves matching model output to the vector representing the correct label. While label embedding has been successfully applied in extreme classification and zero-shot learning, and offers both computational and statistical advantages, its theoretical foundations remain poorly understood. This work presents an analysis of label embedding in the context of extreme multiclass classification, where the number of classes $C$ is very large. We present an excess risk bound that reveals a trade-off between computational and statistical efficiency, quantified via the coherence of the embedding matrix. We further show that under the Massart noise condition, the statistical penalty for label embedding vanishes with sufficiently low coherence. Our analysis supports an algorithm that is simple, scalable, and easily parallelizable, and experimental results demonstrate its effectiveness in large-scale applications.

NeurIPS Conference 2024 Conference Paper

Label Noise: Ignorance Is Bliss

• Yilun Zhu
• Jianxin Zhang
• Aditya Gangrade
• Clayton Scott

We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift. We introduce the concept of \emph{relative signal strength} (RSS), a pointwise measure that quantifies the transferability from noisy to clean posterior. Using RSS, we establish nearly matching upper and lower bounds on the excess risk. Our theoretical findings support the simple \emph{Noise Ignorant Empirical Risk Minimization (NI-ERM)} principle, which minimizes empirical risk while ignoring label noise. Finally, we translate this theoretical insight into practice: by using NI-ERM to fit a linear classifier on top of a self-supervised feature extractor, we achieve state-of-the-art performance on the CIFAR-N data challenge.

ICML Conference 2024 Conference Paper

Testing the Feasibility of Linear Programs with Bandit Feedback

• Aditya Gangrade
• Aditya Gopalan
• Venkatesh Saligrama
• Clayton Scott

While the recent literature has seen a surge in the study of constrained bandit problems, all existing methods for these begin by assuming the feasibility of the underlying problem. We initiate the study of testing such feasibility assumptions, and in particular address the problem in the linear bandit setting, thus characterising the costs of feasibility testing for an unknown linear program using bandit feedback. Concretely, we test if $\exists x: Ax \ge 0$ for an unknown $A \in \mathbb{R}^{m \times d}$, by playing a sequence of actions $x_t\in \mathbb{R}^d$, and observing $Ax_t + \mathrm{noise}$ in response. By identifying the hypothesis as determining the sign of the value of a minimax game, we construct a novel test based on low-regret algorithms and a nonasymptotic law of iterated logarithms. We prove that this test is reliable, and adapts to the ‘signal level, ’ $\Gamma, $ of any instance, with mean sample costs scaling as $\widetilde{O}(d^2/\Gamma^2)$. We complement this by a minimax lower bound of $\Omega(d/\Gamma^2)$ for sample costs of reliable tests, dominating prior asymptotic lower bounds by capturing the dependence on $d$, and thus elucidating a basic insight missing in the extant literature on such problems.

NeurIPS Conference 2024 Conference Paper

The Implicit Bias of Gradient Descent on Separable Multiclass Data

• Hrithik Ravi
• Clayton Scott
• Daniel Soudry
• Yutong Wang

Implicit bias describes the phenomenon where optimization-based training algorithms, without explicit regularization, show a preference for simple estimators even when more complex estimators have equal objective values. Multiple works have developed the theory of implicit bias for binary classification under the assumption that the loss satisfies an exponential tail property. However, there is a noticeable gap in analysis for multiclass classification, with only a handful of results which themselves are restricted to the cross-entropy loss. In this work, we employ the framework of Permutation Equivariant and Relative Margin-based (PERM) losses [Wang and Scott, 2024] to introduce a multiclass extension of the exponential tail property. This class of losses includes not only cross-entropy but also other losses. Using this framework, we extend the implicit bias result of Soudry et al. [2018] to multiclass classification. Furthermore, our proof techniques closely mirror those of the binary case, thus illustrating the power of the PERM framework for bridging the binary-multiclass gap.

JMLR Journal 2024 Journal Article

Unified Binary and Multiclass Margin-Based Classification

• Yutong Wang
• Clayton Scott

The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

ICML Conference 2023 Conference Paper

Mixture Proportion Estimation Beyond Irreducibility

• Yilun Zhu 0002
• Aaron Fjeldsted
• Darren Holland
• George Landon
• Azaree Lintereur
• Clayton Scott

The task of mixture proportion estimation (MPE) is to estimate the weight of a component distribution in a mixture, given observations from both the component and mixture. Previous work on MPE adopts the irreducibility assumption, which ensures identifiablity of the mixture proportion. In this paper, we propose a more general sufficient condition that accommodates several settings of interest where irreducibility does not hold. We further present a resampling-based meta-algorithm that takes any existing MPE algorithm designed to work under irreducibility and adapts it to work under our more general condition. Our approach empirically exhibits improved estimation performance relative to baseline methods and to a recently proposed regrouping-based algorithm.

ICLR Conference 2022 Conference Paper

VC dimension of partially quantized neural networks in the overparametrized regime

• Yutong Wang 0002
• Clayton Scott

Vapnik-Chervonenkis (VC) theory has so far been unable to explain the small generalization error of overparametrized neural networks. Indeed, existing applications of VC theory to large networks obtain upper bounds on VC dimension that are proportional to the number of weights, and for a large class of networks, these upper bound are known to be tight. In this work, we focus on a class of partially quantized networks that we refer to as hyperplane arrangement neural networks (HANNs). Using a sample compression analysis, we show that HANNs can have VC dimension significantly smaller than the number of weights, while being highly expressive. In particular, empirical risk minimization over HANNs in the overparametrized regime achieves the minimax rate for classification with Lipschitz posterior class probability. We further demonstrate the expressivity of HANNs empirically. On a panel of 121 UCI datasets, overparametrized HANNs are able to match the performance of state-of-the-art full-precision models.

ICML Conference 2021 Conference Paper

An exact solver for the Weston-Watkins SVM subproblem

• Yutong Wang 0002
• Clayton Scott

Recent empirical evidence suggests that the Weston-Watkins support vector machine is among the best performing multiclass extensions of the binary SVM. Current state-of-the-art solvers repeatedly solve a particular subproblem approximately using an iterative strategy. In this work, we propose an algorithm that solves the subproblem exactly using a novel reparametrization of the Weston-Watkins dual problem. For linear WW-SVMs, our solver shows significant speed-up over the state-of-the-art solver when the number of classes is large. Our exact subproblem solver also allows us to prove linear convergence of the overall solver.

JMLR Journal 2021 Journal Article

Domain Generalization by Marginal Transfer Learning

• Gilles Blanchard
• Aniket Anand Deshmukh
• Urun Dogan
• Gyemin Lee
• Clayton Scott

In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future unlabeled data sets that are not known to the learner. This problem arises in several applications where data distributions fluctuate because of environmental, technical, or other sources of variation. We introduce a formal framework for DG, and argue that it can be viewed as a kind of supervised learning problem by augmenting the original feature space with the marginal distribution of feature vectors. While our framework has several connections to conventional analysis of supervised learning algorithms, several unique aspects of DG require new methods of analysis. This work lays the learning theoretic foundations of domain generalization, building on our earlier conference paper where the problem of DG was introduced. We present two formal models of data generation, corresponding notions of risk, and distribution-free generalization error analysis. By focusing our attention on kernel methods, we also provide more quantitative results and a universally consistent algorithm. An efficient implementation is provided for this algorithm, which is experimentally compared to a pooling strategy on one synthetic and three real-world data sets. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

NeurIPS Conference 2020 Conference Paper

Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations

• Alexander Ritchie
• Robert A. Vandermeulen
• Clayton Scott

Recent research has established sufficient conditions for finite mixture models to be identifiable from grouped observations. These conditions allow the mixture components to be nonparametric and have substantial (or even total) overlap. This work proposes an algorithm that consistently estimates any identifiable mixture model from grouped observations. Our analysis leverages an oracle inequality for weighted kernel density estimators of the distribution on groups, together with a general result showing that consistent estimation of the distribution on groups implies consistent estimation of mixture components. A practical implementation is provided for paired observations, and the approach is shown to outperform existing methods, especially when mixture components overlap significantly.

NeurIPS Conference 2020 Conference Paper

Learning from Label Proportions: A Mutual Contamination Framework

• Clayton Scott
• Jianxin Zhang

Learning from label proportions (LLP) is a weakly supervised setting for classification in which unlabeled training instances are grouped into bags, and each bag is annotated with the proportion of each class occurring in that bag. Prior work on LLP has yet to establish a consistent learning procedure, nor does there exist a theoretically justified, general purpose training criterion. In this work we address these two issues by posing LLP in terms of mutual contamination models (MCMs), which have recently been applied successfully to study various other weak supervision settings. In the process, we establish several novel technical results for MCMs, including unbiased losses and generalization error bounds under non-iid sampling plans. We also point out the limitations of a common experimental setting for LLP, and propose a new one based on our MCM framework.

NeurIPS Conference 2020 Conference Paper

Weston-Watkins Hinge Loss and Ordered Partitions

• Yutong Wang
• Clayton Scott

Multiclass extensions of the support vector machine (SVM) have been formulated in a variety of ways. A recent empirical comparison of nine such formulations [Doǧan et al. 2016] recommends the variant proposed by Weston and Watkins (WW), despite the fact that the WW-hinge loss is not calibrated with respect to the 0-1 loss. In this work we introduce a novel discrete loss function for multiclass classification, the ordered partition loss, and prove that the WW-hinge loss is calibrated with respect to this loss. We also argue that the ordered partition loss is minimally emblematic among discrete losses satisfying this property. Finally, we apply our theory to justify the empirical observation made by Doǧan et al that the WW-SVM can work well even under massive label noise, a challenging setting for multiclass SVMs.

JMLR Journal 2019 Journal Article

Decontamination of Mutual Contamination Models

• Julian Katz-Samuels
• Gilles Blanchard
• Clayton Scott

Many machine learning problems can be characterized by \emph{mutual contamination models}. In these problems, one observes several random samples from different convex combinations of a set of unknown base distributions and the goal is to infer these base distributions. This paper considers the general setting where the base distributions are defined on arbitrary probability spaces. We examine three popular machine learning problems that arise in this general setting: multiclass classification with label noise, demixing of mixed membership models, and classification with partial labels. In each case, we give sufficient conditions for identifiability and present algorithms for the infinite and finite sample settings, with associated performance guarantees. [abs] [ pdf ][ bib ] &copy JMLR 2019. ( edit, beta )

ICML Conference 2018 Conference Paper

Feasible Arm Identification

• Julian Katz-Samuels
• Clayton Scott

We introduce the feasible arm identification problem, a pure exploration multi-armed bandit problem where the agent is given a set of $D$-dimensional arms and a polyhedron $P = \{x: A x \leq b \} \subset R^D$. Pulling an arm gives a random vector and the goal is to determine, using a fixed budget of $T$ pulls, which of the arms have means belonging to $P$. We propose three algorithms MD-UCBE, MD-SAR, and MD-APT and provide a unified analysis establishing upper bounds for each of them. We also establish a lower bound that matches up to constants the upper bounds of MD-UCBE and MD-APT. Finally, we demonstrate the effectiveness of our algorithms on synthetic and real-world datasets.

ICML Conference 2016 Conference Paper

Mixture Proportion Estimation via Kernel Embeddings of Distributions

• Harish G. Ramaswamy
• Clayton Scott
• Ambuj Tewari

Mixture proportion estimation (MPE) is the problem of estimating the weight of a component distribution in a mixture, given samples from the mixture and component. This problem constitutes a key part in many "weakly supervised learning" problems like learning with positive and unlabelled samples, learning with label noise, anomaly detection and crowdsourcing. While there have been several methods proposed to solve this problem, to the best of our knowledge no efficient algorithm with a proven convergence rate towards the true proportion exists for this problem. We fill this gap by constructing a provably correct algorithm for MPE, and derive convergence rates under certain assumptions on the distribution. Our method is based on embedding distributions onto an RKHS, and implementing it only requires solving a simple convex quadratic programming problem a few times. We run our algorithm on several standard classification datasets, and demonstrate that it performs comparably to or better than other algorithms on most datasets.

YNIMG Journal 2014 Journal Article

Disease prediction based on functional connectomes using a scalable and spatially-informed support vector machine

• Takanori Watanabe
• Daniel Kessler
• Clayton Scott
• Michael Angstadt
• Chandra Sripada

Substantial evidence indicates that major psychiatric disorders are associated with distributed neural dysconnectivity, leading to a strong interest in using neuroimaging methods to accurately predict disorder status. In this work, we are specifically interested in a multivariate approach that uses features derived from whole-brain resting state functional connectomes. However, functional connectomes reside in a high dimensional space, which complicates model interpretation and introduces numerous statistical and computational challenges. Traditional feature selection techniques are used to reduce data dimensionality, but are blind to the spatial structure of the connectomes. We propose a regularization framework where the 6-D structure of the functional connectome (defined by pairs of points in 3-D space) is explicitly taken into account via the fused Lasso or the GraphNet regularizer. Our method only restricts the loss function to be convex and margin-based, allowing non-differentiable loss functions such as the hinge-loss to be used. Using the fused Lasso or GraphNet regularizer with the hinge-loss leads to a structured sparse support vector machine (SVM) with embedded feature selection. We introduce a novel efficient optimization algorithm based on the augmented Lagrangian and the classical alternating direction method, which can solve both fused Lasso and GraphNet regularized SVM with very little modification. We also demonstrate that the inner subproblems of the algorithm can be solved efficiently in analytic form by coupling the variable splitting strategy with a data augmentation scheme. Experiments on simulated data and resting state scans from a large schizophrenia dataset show that our proposed approach can identify predictive regions that are spatially contiguous in the 6-D “connectome space, ” offering an additional layer of interpretability that could provide new insights about various disease processes.

NeurIPS Conference 2014 Conference Paper

Robust Kernel Density Estimation by Scaling and Projection in Hilbert Space

• Robert Vandermeulen
• Clayton Scott

While robust parameter estimation has been well studied in parametric density estimation, there has been little investigation into robust density estimation in the nonparametric setting. We present a robust version of the popular kernel density estimator (KDE). As with other estimators, a robust version of the KDE is useful since sample contamination is a common issue with datasets. What ``robustness'' means for a nonparametric density estimate is not straightforward and is a topic we explore in this paper. To construct a robust KDE we scale the traditional KDE and project it to its nearest weighted KDE in the $L^2$ norm. Because the squared $L^2$ norm penalizes point-wise errors superlinearly this causes the weighted KDE to allocate more weight to high density regions. We demonstrate the robustness of the SPKDE with numerical experiments and a consistency result which shows that asymptotically the SPKDE recovers the uncontaminated density under sufficient conditions on the contamination.

YNIMG Journal 2013 Journal Article

Distributed effects of methylphenidate on the network structure of the resting brain: A connectomic pattern classification analysis

• Chandra Sekhar Sripada
• Daniel Kessler
• Robert Welsh
• Michael Angstadt
• Israel Liberzon
• K. Luan Phan
• Clayton Scott

Methylphenidate is a psychostimulant medication that produces improvements in functions associated with multiple neurocognitive systems. To investigate the potentially distributed effects of methylphenidate on the brain's intrinsic network architecture, we coupled resting state imaging with multivariate pattern classification. In a within-subject, double-blind, placebo-controlled, randomized, counterbalanced, cross-over design, 32 healthy human volunteers received either methylphenidate or placebo prior to two fMRI resting state scans separated by approximately one week. Resting state connectomes were generated by placing regions of interest at regular intervals throughout the brain, and these connectomes were submitted for support vector machine analysis. We found that methylphenidate produces a distributed, reliably detected, multivariate neural signature. Methylphenidate effects were evident across multiple resting state networks, especially visual, somatomotor, and default networks. Methylphenidate reduced coupling within visual and somatomotor networks. In addition, default network exhibited decoupling with several task positive networks, consistent with methylphenidate modulation of the competitive relationship between these networks. These results suggest that connectivity changes within and between large-scale networks are potentially involved in the mechanisms by which methylphenidate improves attention functioning.

UAI Conference 2011 Conference Paper

Active Diagnosis via AUC Maximization: An Efficient Approach for Multiple Fault Identification in Large Scale, Noisy Networks

• Gowtham Bellala
• Jason Stanley
• Clayton Scott
• Suresh K. Bhavnani

The problem of active diagnosis arises in several applications such as disease diagnosis, and fault diagnosis in computer networks, where the goal is to rapidly identify the binary states of a set of objects (e.g., faulty or working) by sequentially selecting, and observing, (noisy) responses to binary valued queries. Current algorithms in this area rely on loopy belief propagation for active query selection. These algorithms have an exponential time complexity, making them slow and even intractable in large networks. We propose a rank-based greedy algorithm that sequentially chooses queries such that the area under the ROC curve of the rank-based output is maximized. The AUC criterion allows us to make a simplifying assumption that significantly reduces the complexity of active query selection (from exponential to near quadratic), with little or no compromise on the performance quality.

NeurIPS Conference 2011 Conference Paper

Generalizing from Several Related Classification Tasks to a New Unlabeled Sample

• Gilles Blanchard
• Gyemin Lee
• Clayton Scott

We consider the problem of assigning class labels to an unlabeled test data set, given several labeled training data sets drawn from similar distributions. This problem arises in several applications where data distributions fluctuate because of biological, technical, or other sources of variation. We develop a distribution-free, kernel-based approach to the problem. This approach involves identifying an appropriate reproducing kernel Hilbert space and optimizing a regularized empirical risk over the space. We present generalization error analysis, describe universal kernels, and establish universal consistency of the proposed methodology. Experimental results on flow cytometry data are presented.

ICML Conference 2011 Conference Paper

On the Robustness of Kernel Density M-Estimators

• JooSeuk Kim
• Clayton Scott

ICML Conference 2011 Conference Paper

Surrogate losses and regret bounds for cost-sensitive classification with example-dependent costs

• Clayton Scott

NeurIPS Conference 2010 Conference Paper

Extensions of Generalized Binary Search to Group Identification and Exponential Costs

• Gowtham Bellala
• Suresh Bhavnani
• Clayton Scott

Generalized Binary Search (GBS) is a well known greedy algorithm for identifying an unknown object while minimizing the number of yes" or "no" questions posed about that object, and arises in problems such as active learning and active diagnosis. Here, we provide a coding-theoretic interpretation for GBS and show that GBS can be viewed as a top-down algorithm that greedily minimizes the expected number of queries required to identify an object. This interpretation is then used to extend GBS in two ways. First, we consider the case where the objects are partitioned into groups, and the objective is to identify only the group to which the object belongs. Then, we consider the case where the cost of identifying an object grows exponentially in the number of queries. In each case, we present an exact formula for the objective function involving Shannon or Renyi entropy, and develop a greedy algorithm for minimizing it. "

JMLR Journal 2010 Journal Article

Semi-Supervised Novelty Detection

• Gilles Blanchard
• Gyemin Lee
• Clayton Scott

A common setting for novelty detection assumes that labeled examples from the nominal class are available, but that labeled examples of novelties are unavailable. The standard (inductive) approach is to declare novelties where the nominal density is low, which reduces the problem to density level set estimation. In this paper, we consider the setting where an unlabeled and possibly contaminated sample is also available at learning time. We argue that novelty detection in this semi-supervised setting is naturally solved by a general reduction to a binary classification problem. In particular, a detector with a desired false positive rate can be achieved through a reduction to Neyman-Pearson classification. Unlike the inductive approach, semi-supervised novelty detection (SSND) yields detectors that are optimal (e.g., statistically consistent) regardless of the distribution on novelties. Therefore, in novelty detection, unlabeled data have a substantial impact on the theoretical properties of the decision rule. We validate the practical utility of SSND with an extensive experimental study. We also show that SSND provides distribution-free, learning-theoretic solutions to two well known problems in hypothesis testing. First, our results provide a general solution to the general two-sample problem, that is, the problem of determining whether two random samples arise from the same distribution. Second, a specialization of SSND coincides with the standard p -value approach to multiple testing under the so-called random effects model. Unlike standard rejection regions based on thresholded p -values, the general SSND framework allows for adaptation to arbitrary alternative distributions in multiple dimensions. [abs] [ pdf ][ bib ] &copy JMLR 2010. ( edit, beta )

NeurIPS Conference 2008 Conference Paper

Performance analysis for L\_2 kernel classification

• JooSeuk Kim
• Clayton Scott

We provide statistical performance guarantees for a recently introduced kernel classifier that optimizes the $L_2$ or integrated squared error (ISE) of a difference of densities. The classifier is similar to a support vector machine (SVM) in that it is the solution of a quadratic program and yields a sparse classifier. Unlike SVMs, however, the $L_2$ kernel classifier does not involve a regularization parameter. We prove a distribution free concentration inequality for a cross-validation based estimate of the ISE, and apply this result to deduce an oracle inequality and consistency of the classifier on the sense of both ISE and probability of error. Our results can also be specialized to give performance guarantees for an existing method of $L_2$ kernel density estimation.

NeurIPS Conference 2005 Conference Paper

Learning Minimum Volume Sets

• Clayton Scott
• Robert Nowak

Given a probability measure P and a reference measure µ, one is often interested in the minimum µ-measure set with P -measure at least α. Minimum volume sets of this type summarize the regions of greatest probability mass of P, and are useful for detecting anoma- lies and constructing confidence regions. This paper addresses the problem of estimating minimum volume sets based on independent samples distributed according to P. Other than these samples, no other information is available regarding P, but the reference mea- sure µ is assumed to be known. We introduce rules for estimating minimum volume sets that parallel the empirical risk minimization and structural risk minimization principles in classification. As in classification, we show that the performances of our estimators are controlled by the rate of uniform convergence of empirical to true probabilities over the class from which the estimator is drawn. Thus we obtain finite sample size performance bounds in terms of VC dimension and related quantities. We also demonstrate strong universal consistency and an oracle inequality. Estimators based on histograms and dyadic partitions illustrate the proposed rules.

NeurIPS Conference 2004 Conference Paper

On the Adaptive Properties of Decision Trees

• Clayton Scott
• Robert Nowak

Decision trees are surprisingly adaptive in three important respects: They automatically (1) adapt to favorable conditions near the Bayes decision boundary; (2) focus on data distributed on lower dimensional manifolds; (3) reject irrelevant features. In this paper we examine a decision tree based on dyadic splits that adapts to each of these conditions to achieve minimax optimal rates of convergence. The proposed classifier is the first known to achieve these optimal rates while being practical and im- plementable.

NeurIPS Conference 2003 Conference Paper

Near-Minimax Optimal Classification with Dyadic Classification Trees

• Clayton Scott
• Robert Nowak

This paper reports on a family of computationally practical classifiers that converge to the Bayes error at near-minimax optimal rates for a va- riety of distributions. The classifiers are based on dyadic classification trees (DCTs), which involve adaptively pruned partitions of the feature space. A key aspect of DCTs is their spatial adaptivity, which enables lo- cal (rather than global) fitting of the decision boundary. Our risk analysis involves a spatial decomposition of the usual concentration inequalities, leading to a spatially adaptive, data-dependent pruning criterion. For any distribution on (X, Y ) whose Bayes decision boundary behaves locally like a Lipschitz smooth function, we show that the DCT error converges to the Bayes error at a rate within a logarithmic factor of the minimax optimal rate. We also study DCTs equipped with polynomial classifica- tion rules at each leaf, and show that as the smoothness of the boundary increases their errors converge to the Bayes error at a rate approaching n−1/2, the parametric rate. We are not aware of any other practical classi- fiers that provide similar rate of convergence guarantees. Fast algorithms for tree pruning are discussed.

NeurIPS Conference 2002 Conference Paper

Dyadic Classification Trees via Structural Risk Minimization

• Clayton Scott
• Robert Nowak

Classification trees are one of the most popular types of classifiers, with ease of implementation and interpretation being among their attractive features. Despite the widespread use of classification trees, theoretical analysis of their performance is scarce. In this paper, we show that a new family of classification trees, called dyadic classification trees (DCTs), are near optimal (in a minimax sense) for a very broad range of clas- sification problems. This demonstrates that other schemes (e. g. , neural networks, support vector machines) cannot perform significantly better than DCTs in many cases. We also show that this near optimal perfor- mance is attained with linear (in the number of training data) complexity growing and pruning algorithms. Moreover, the performance of DCTs on benchmark datasets compares favorably to that of standard CART, which is generally more computationally intensive and which does not possess similar near optimality properties. Our analysis stems from the- oretical results on structural risk minimization, on which the pruning rule for DCTs is based.