English
Related papers

Related papers: General Loss Functions Lead to (Approximate) Inter…

200 papers

Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data. To bridge this gap, we…

Machine Learning · Statistics 2021-09-13 Hao Liu , Minshuo Chen , Tuo Zhao , Wenjing Liao

We address the problem of aggregating an ensemble of predictors with known loss bounds in a semi-supervised binary classification setting, to minimize prediction loss incurred on the unlabeled data. We find the minimax optimal predictions…

Machine Learning · Computer Science 2016-11-08 Akshay Balsubramani , Yoav Freund

It is well-known that every convex function admits an affine support at every interior point of a domain. Convex functions of higher order (precisely of an odd order) have a similar property: they are supported by the polynomials of degree…

Functional Analysis · Mathematics 2008-07-28 Szymon Wasowicz

We establish strong duality relations for functional two-step compositional risk-constrained learning problems with multiple nonconvex loss functions and/or learning constraints, regardless of nonconvexity and under a minimal set of…

Machine Learning · Computer Science 2023-12-05 Dionysis Kalogerias , Spyridon Pougkakiotis

Super-resolution of LiDAR range images is crucial to improving many downstream tasks such as object detection, recognition, and tracking. While deep learning has made a remarkable advances in super-resolution techniques, typical…

Robotics · Computer Science 2022-03-15 Youngsun Kwon , Minhyuk Sung , Sung-Eui Yoon

Motivated by the extensive application of approximate gradients in machine learning and optimization, we investigate inexact subgradient methods subject to persistent additive errors. Within a nonconvex semialgebraic framework, assuming…

Optimization and Control · Mathematics 2025-05-14 Jérôme Bolte , Tam Le , Éric Moulines , Edouard Pauwels

We explore some mathematical features of the loss landscape of overparameterized neural networks. A priori one might imagine that the loss function looks like a typical function from $\mathbb{R}^n$ to $\mathbb{R}$ - in particular,…

Machine Learning · Computer Science 2018-04-27 Y Cooper

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a…

Optimization and Control · Mathematics 2025-09-24 Po Chen , Rujun Jiang , Peng Wang

This paper explores the implicit bias of overparameterized neural networks of depth greater than two layers. Our framework considers a family of networks of varying depth that all have the same capacity but different implicitly defined…

Machine Learning · Computer Science 2022-02-03 Greg Ongie , Rebecca Willett

This paper proposes a novel preconditioned implicit-explicit algorithm enhanced with the extrapolation technique for non-convex optimization problems. The algorithm employs a third-order Adams-Bashforth scheme for the nonlinear and explicit…

Optimization and Control · Mathematics 2025-09-19 Kelin Wu , Hongpeng Sun

The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the properties of the loss function. The most decisive among these…

Machine Learning · Computer Science 2025-10-31 Tomas Hrycej , Bernhard Bermeitinger , Massimo Pavone , Götz-Henrik Wiegand , Siegfried Handschuh

Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more flexible forms, and should be tailored for…

Computer Vision and Pattern Recognition · Computer Science 2022-05-12 Zhaoqi Leng , Mingxing Tan , Chenxi Liu , Ekin Dogus Cubuk , Xiaojie Shi , Shuyang Cheng , Dragomir Anguelov

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

A deep equilibrium model uses implicit layers, which are implicitly defined through an equilibrium point of an infinite sequence of computation. It avoids any explicit computation of the infinite sequence by finding an equilibrium point…

Machine Learning · Computer Science 2021-02-19 Kenji Kawaguchi

Proxy-based metric learning losses are superior to pair-based losses due to their fast convergence and low training complexity. However, existing proxy-based losses focus on learning class-discriminative features while overlooking the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Zhibo Yang , Muhammet Bastan , Xinliang Zhu , Doug Gray , Dimitris Samaras

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

Machine Learning · Computer Science 2022-07-20 David G. T. Barrett , Benoit Dherin

Many statistical problems include model parameters that are defined as the solutions to optimization sub-problems. These include classical approaches such as profile likelihood as well as modern applications involving flow networks or…

Methodology · Statistics 2025-03-17 Cheng Zeng , Yaozhi Yang , Jason Xu , Leo L Duan

We consider a commonly studied supervised classification of a synthetic dataset whose labels are generated by feeding a one-layer neural network with random iid inputs. We study the generalization performances of standard classifiers in the…

Machine Learning · Statistics 2021-02-18 Benjamin Aubin , Florent Krzakala , Yue M. Lu , Lenka Zdeborová

Large over-parametrized models learned via stochastic gradient descent (SGD) methods have become a key element in modern machine learning. Although SGD methods are very effective in practice, most theoretical analyses of SGD suggest slower…

Optimization and Control · Mathematics 2018-11-08 Raef Bassily , Mikhail Belkin , Siyuan Ma