English
Related papers

Related papers: Linear-Core Surrogates: Smooth Loss Functions with…

200 papers

Many neural networks deployed in the real world scenarios are trained using cross entropy based loss functions. From the optimization perspective, it is known that the behavior of first order methods such as gradient descent crucially…

Machine Learning · Computer Science 2023-10-09 Zhu Wang , Praveen Raj Veluswami , Harsh Mishra , Sathya N. Ravi

Contrastive representation learning encourages data representation to make semantically similar pairs closer than randomly drawn negative samples, which has been successful in various domains such as vision, language, and graphs. Recent…

Machine Learning · Computer Science 2022-05-31 Han Bao , Yoshihiro Nagano , Kento Nozawa

Multi-label loss functions are usually non-differentiable, requiring surrogate loss functions for gradient-based optimisation. The consistency of surrogate loss functions is not proven and is exacerbated by the conflicting nature of…

Machine Learning · Computer Science 2024-02-02 Kaan Demir , Bach Nguyen , Bing Xue , Mengjie Zhang

Problem decomposition plays a vital role when applying cooperative coevolution (CC) to large scale global optimization problems. However, most learning-based decomposition algorithms either only apply to additively separable problems or…

Neural and Evolutionary Computing · Computer Science 2021-01-20 An Chen , Zhigang Ren , Muyi Wang , Yongsheng Liang , Hanqing Liu , Wenhao Du

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

In a multi-class classification problem, it is standard to model the output of a neural network as a categorical distribution conditioned on the inputs. The output must therefore be positive and sum to one, which is traditionally enforced…

Neural and Evolutionary Computing · Computer Science 2016-03-01 Alexandre de Brébisson , Pascal Vincent

We study a set of regularization methods for high-dimensional linear regression models. These penalized estimators have the square root of the residual sum of squared errors as loss function, and any weakly decomposable norm as penalty…

Statistics Theory · Mathematics 2016-06-28 Benjamin Stucky , Sara van de Geer

We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate modeling, our surrogates retain the interpretable structure and…

Developing effective surrogates (performance predictors) for Neural Architecture Search (NAS) typically requires expensive fine-tuning or the engineering of complex representations. We propose a low-cost embedding strategy that leverages…

Machine Learning · Computer Science 2026-05-18 Pranav Somu , Advay Balakrishnan , Stepan Kravtsov , Aaron McDaniel , Jason Zutty

We introduce UniLoss, a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses. Our key observation is that in many cases,…

Computer Vision and Pattern Recognition · Computer Science 2020-07-29 Lanlan Liu , Mingzhe Wang , Jia Deng

We consider supervised learning problems in which set predictions provide explicit uncertainty estimates. Using Choquet integrals (a.k.a. Lov{\'a}sz extensions), we propose a convex loss function for nondecreasing subset-valued functions…

Machine Learning · Computer Science 2025-12-23 Francis Bach

This work proposes a data-driven surrogate modeling framework for cost-effectively inferring the torque of a permanent magnet synchronous machine under geometric design variations. The framework is separated into a reduced-order modeling…

Computational Engineering, Finance, and Science · Computer Science 2025-03-13 Aylar Partovizadeh , Sebastian Schöps , Dimitrios Loukrezis

The problem of learning to defer with multiple experts consists of optimally assigning input instances to experts, balancing the trade-off between their accuracy and computational cost. This is a critical challenge in natural language…

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

Widely used loss functions for CNN segmentation, e.g., Dice or cross-entropy, are based on integrals over the segmentation regions. Unfortunately, for highly unbalanced segmentations, such regional summations have values that differ by…

Image and Video Processing · Electrical Eng. & Systems 2020-10-20 Hoel Kervadec , Jihene Bouchtiba , Christian Desrosiers , Eric Granger , Jose Dolz , Ismail Ben Ayed

In various approaches to learning, notably in domain adaptation, active learning, learning under covariate shift, semi-supervised learning, learning with concept drift, and the like, one often wants to compare a baseline classifier to one…

Machine Learning · Computer Science 2017-07-14 Marco Loog , Jesse H. Krijthe , Are C. Jensen

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

We extend recent computer-assisted design and analysis techniques for first-order optimization over structured functions--known as performance estimation--to apply to structured sets. We prove "interpolation theorems" for smooth and…

Optimization and Control · Mathematics 2024-11-20 Alan Luner , Benjamin Grimmer

Surrogate models, crucial for approximating complex simulation data across sciences, inherently carry uncertainties that range from simulation noise to model prediction errors. Without rigorous uncertainty quantification, predictions become…

Machine Learning · Statistics 2025-04-07 Yuhan Duan , Xin Zhao , Neng Shi , Han-Wei Shen

The Area Under the Curve (AUC) is an important performance metric for classification tasks, particularly in class-imbalanced scenarios. However, minimizing the AUC presents significant challenges due to the non-convex and discontinuous…

Machine Learning · Computer Science 2025-10-27 JunRu Luo , Difei Cheng , Bo Zhang

Discrete optimization belongs to the set of $\mathcal{NP}$-hard problems, spanning fields such as mixed-integer programming and combinatorial optimization. A current standard approach to solving convex discrete optimization problems is the…

Machine Learning · Computer Science 2024-02-28 Kyle Mana , Fernando Acero , Stephen Mak , Parisa Zehtabi , Michael Cashmore , Daniele Magazzeni , Manuela Veloso