English
Related papers

Related papers: An Embedding Framework for the Design and Analysis…

200 papers

We study the consistency of surrogate risks for robust binary classification. It is common to learn robust classifiers by adversarial training, which seeks to minimize the expected $0$-$1$ loss when each example can be maliciously corrupted…

Machine Learning · Computer Science 2025-10-09 Natalie Frank , Jonathan Niles-Weed

We introduce a new surrogate loss function called orbit loss in the structured prediction framework, which has good theoretical and practical advantages. While the orbit loss is not convex, it has a simple analytical gradient and a simple…

Machine Learning · Computer Science 2015-12-10 Danny Karmon , Joseph Keshet

We propose and analyze a novel theoretical and algorithmic framework for structured prediction. While so far the term has referred to discrete output spaces, here we consider more general settings, such as manifolds or spaces of probability…

Machine Learning · Statistics 2020-02-14 Carlo Ciliberto , Lorenzo Rosasco , Alessandro Rudi

Crash simulations play an essential role in improving vehicle safety, design optimization, and injury risk estimation. Unfortunately, numerical solutions of such problems using state-of-the-art high-fidelity models require significant…

Machine Learning · Computer Science 2024-02-16 Jonas Kneifl , Jörg Fehr , Steven L. Brunton , J. Nathan Kutz

Recent research has introduced a key notion of $H$-consistency bounds for surrogate losses. These bounds offer finite-sample guarantees, quantifying the relationship between the zero-one estimation error (or other target loss) and the…

Machine Learning · Computer Science 2025-12-30 Anqi Mao , Mehryar Mohri , Yutao Zhong

A powerful and flexible approach to structured prediction consists in embedding the structured objects to be predicted into a feature space of possibly infinite dimension by means of output kernels, and then, solving a regression problem in…

Machine Learning · Statistics 2020-11-03 Luc Brogat-Motte , Alessandro Rudi , Céline Brouard , Juho Rousu , Florence d'Alché-Buc

The F-measure is a widely used performance measure for multi-label classification, where multiple labels can be active in an instance simultaneously (e.g. in image tagging, multiple tags can be active in any image). In particular, the…

Machine Learning · Statistics 2020-09-17 Mingyuan Zhang , Harish G. Ramaswamy , Shivani Agarwal

Surrogate models are used to reduce the burden of expensive-to-evaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be…

Neural and Evolutionary Computing · Computer Science 2019-07-17 Alexander Hagg , Martin Zaefferer , Jörg Stork , Adam Gaier

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Hugo Proença , Ehsan Yaghoubi , Pendar Alirezazadeh

The Polyak stepsize has been proven to be a fundamental stepsize in convex optimization, giving near optimal gradient descent rates across a wide range of assumptions. The universality of the Polyak stepsize has also inspired many…

Optimization and Control · Mathematics 2026-01-22 Francesco Orabona , Ryan D'Orazio

A fundamental challenge in machine learning is the choice of a loss as it characterizes our learning task, is minimized in the training phase, and serves as an evaluation criterion for estimators. Proper losses are commonly chosen, ensuring…

Machine Learning · Statistics 2026-03-04 Han Bao , Asuka Takatsu

The top-$k$ error is often employed to evaluate performance for challenging classification tasks in computer vision as it is designed to compensate for ambiguity in ground truth labels. This practical success motivates our theoretical…

Machine Learning · Computer Science 2020-07-09 Forest Yang , Sanmi Koyejo

We consider the hashing mechanism for constructing binary embeddings, that involves pseudo-random projections followed by nonlinear (sign function) mappings. The pseudo-random projection is described by a matrix, where not all entries are…

Machine Learning · Computer Science 2016-07-04 Anna Choromanska , Krzysztof Choromanski , Mariusz Bojarski , Tony Jebara , Sanjiv Kumar , Yann LeCun

We propose a general approach for supervised learning with structured output spaces, such as combinatorial and polyhedral sets, that is based on minimizing estimated conditional risk functions. Given a loss function defined over pairs of…

Machine Learning · Statistics 2017-02-28 Chong Yang Goh , Patrick Jaillet

An embedding is a mapping from a set of nodes of a network into a real vector space. Embeddings can have various aims like capturing the underlying graph topology and structure, node-to-node relationship, or other relevant information about…

Machine Learning · Computer Science 2023-06-21 Ashkan Dehghan , Kinga Siuta , Agata Skorupka , Andrei Betlen , David Miller , Bogumil Kaminski , Pawel Pralat

The present paper proposes a Bayesian framework for inverse problems that seamlessly integrates optimization and inversion to enable rapid surrogate modeling, accurate parameter inference, and rigorous uncertainty quantification. Bayesian…

Computational Engineering, Finance, and Science · Computer Science 2026-02-05 Mihaela Chiappetta , Massimo Carraturo , Alexander Raßloff , Markus Kästner , Ferdinando Auricchio

Convex regression is the problem of fitting a convex function to a data set consisting of input-output pairs. We present a new approach to this problem called spectrahedral regression, in which we fit a spectrahedral function to the data,…

Optimization and Control · Mathematics 2021-11-01 Eliza O'Reilly , Venkat Chandrasekaran

Unsupervised representation learning methods are widely used for gaining insight into high-dimensional, unstructured, or structured data. In some cases, users may have prior topological knowledge about the data, such as a known cluster…

Machine Learning · Computer Science 2023-11-08 Edith Heiter , Robin Vandaele , Tijl De Bie , Yvan Saeys , Jefrey Lijffijt

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the…

Machine Learning · Computer Science 2022-03-01 Tao Huang , Zekang Li , Hua Lu , Yong Shan , Shusheng Yang , Yang Feng , Fei Wang , Shan You , Chang Xu

We propose in this paper a general framework for deriving loss functions for structured prediction. In our framework, the user chooses a convex set including the output space and provides an oracle for projecting onto that set. Given that…

Machine Learning · Statistics 2020-02-27 Mathieu Blondel