English
Related papers

Related papers: Approximate Inference via Weighted Rademacher Comp…

200 papers

We study the sample complexity of learning ReLU neural networks from the point of view of generalization. Given norm constraints on the weight matrices, a common approach is to estimate the Rademacher complexity of the associated function…

Machine Learning · Computer Science 2024-02-06 Mark Sellke

We introduce the technique of generic chaining and majorizing measures for controlling sequential Rademacher complexity. We relate majorizing measures to the notion of fractional covering numbers, which we show to be dominated in terms of…

Machine Learning · Statistics 2021-02-04 Adam Block , Yuval Dagan , Sasha Rakhlin

Existing Rademacher complexity bounds for neural networks rely only on norm control of the weight matrices and depend exponentially on depth via a product of the matrix norms. Lower bounds show that this exponential dependence on depth is…

Machine Learning · Computer Science 2020-04-13 Colin Wei , Tengyu Ma

We consider a problem of risk estimation for large-margin multi-class classifiers. We propose a novel risk bound for the multi-class classification problem. The bound involves the marginal distribution of the classifier and the Rademacher…

Machine Learning · Statistics 2021-09-15 Yury Maximov , Daria Reshetova

This paper proposes a simple approach to derive efficient error bounds for learning multiple components with sparsity-inducing regularization. We show that for such regularization schemes, known decompositions of the Rademacher complexity…

Machine Learning · Statistics 2020-01-24 Fabien Lauer

We consider a setting where an agent's uncertainty is represented by a set of probability measures, rather than a single measure. Measure-bymeasure updating of such a set of measures upon acquiring new information is well-known to suffer…

Computer Science and Game Theory · Computer Science 2013-02-26 Joseph Y. Halpern , Samantha Leung

Transductive learning considers situations when a learner observes $m$ labelled training points and $u$ unlabelled test points with the final goal of giving correct answers for the test points. This paper introduces a new complexity measure…

Machine Learning · Statistics 2016-02-24 Ilya Tolstikhin , Nikita Zhivotovskiy , Gilles Blanchard

Various iterative reconstruction algorithms for inverse problems can be unfolded as neural networks. Empirically, this approach has often led to improved results, but theoretical guarantees are still scarce. While some progress on…

Statistics Theory · Mathematics 2021-08-16 Arash Behboodi , Holger Rauhut , Ekkehard Schnoor

Generalized linear mixed models are useful in studying hierarchical data with possibly non-Gaussian responses. However, the intractability of likelihood functions poses challenges for estimation. We develop a new method suitable for this…

Methodology · Statistics 2022-01-26 Zexi Song , Zhiqiang Tan

We reveal a connection between the incompressibility method and the Lovasz local lemma in the context of Ramsey theory. We obtain bounds by repeatedly encoding objects of interest and thereby compressing strings. The method is demonstrated…

Combinatorics · Mathematics 2008-04-07 Pascal Schweitzer

For a finite function class we describe the large sample limit of the sequential Rademacher complexity in terms of the viscosity solution of a $G$-heat equation. In the language of Peng's sublinear expectation theory, the same quantity…

Machine Learning · Computer Science 2016-05-13 Dmitry B. Rokhlin

Set-valued prediction is a well-known concept in multi-class classification. When a classifier is uncertain about the class label for a test instance, it can predict a set of classes instead of a single class. In this paper, we focus on…

Machine Learning · Computer Science 2022-03-15 Thomas Mortier , Eyke Hüllermeier , Krzysztof Dembczyński , Willem Waegeman

Multi-class classification methods that produce sets of probabilistic classifiers, such as ensemble learning methods, are able to model aleatoric and epistemic uncertainty. Aleatoric uncertainty is then typically quantified via the Bayes…

Machine Learning · Statistics 2023-04-20 Thomas Mortier , Viktor Bengs , Eyke Hüllermeier , Stijn Luca , Willem Waegeman

Estimating causal effects from observational network data is a significant but challenging problem. Existing works in causal inference for observational network data lack an analysis of the generalization bound, which can theoretically…

Machine Learning · Computer Science 2023-08-09 Ruichu Cai , Zeqin Yang , Weilin Chen , Yuguang Yan , Zhifeng Hao

We introduce a new sample complexity measure, which we refer to as split-sample growth rate. For any hypothesis $H$ and for any sample $S$ of size $m$, the split-sample growth rate $\hat{\tau}_H(m)$ counts how many different hypotheses can…

Computer Science and Game Theory · Computer Science 2017-04-18 Vasilis Syrgkanis

When randomized ensembles such as bagging or random forests are used for binary classification, the prediction error of the ensemble tends to decrease and stabilize as the number of classifiers increases. However, the precise relationship…

Probability · Mathematics 2019-05-01 Miles E. Lopes

This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This…

Machine Learning · Computer Science 2012-02-20 Corinna Cortes , Mehryar Mohri , Afshin Rostamizadeh

Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is…

Machine Learning · Computer Science 2019-06-14 Deborah Cohen , Amit Daniely , Amir Globerson , Gal Elidan

High complexity models are notorious in machine learning for overfitting, a phenomenon in which models well represent data but fail to generalize an underlying data generating process. A typical procedure for circumventing overfitting…

Machine Learning · Statistics 2025-03-11 James Schmidt

We consider estimating the parameters of a Gaussian mixture density with a given number of components best representing a given set of weighted samples. We adopt a density interpretation of the samples by viewing them as a discrete Dirac…

Machine Learning · Statistics 2025-04-03 Daniel Frisch , Uwe D. Hanebeck