English
Related papers

Related papers: Differentiable Zero-One Loss via Hypersimplex Proj…

200 papers

The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the specific regression or classification task at hand. We reduce the complexity of algorithm design for…

Optimization and Control · Mathematics 2016-05-23 Zeyuan Allen-Zhu , Elad Hazan

Single-objective black box optimization (also known as zeroth-order optimization) is the process of minimizing a scalar objective $f(x)$, given evaluations at adaptively chosen inputs $x$. In this paper, we consider multi-objective…

Machine Learning · Computer Science 2020-06-11 Daniel Golovin , Qiuyi Zhang

In this study, we propose an innovative dynamic classification algorithm aimed at achieving zero missed detections and minimal false positives,acritical in safety-critical domains (e.g., medical diagnostics) where undetected cases risk…

Machine Learning · Computer Science 2025-06-02 Ziyuan Zhong , Junyang Zhou

We introduce new diversification methods for zero-one optimization that significantly extend strategies previously introduced in the setting of metaheuristic search. Our methods incorporate easily implemented strategies for partitioning…

Artificial Intelligence · Computer Science 2017-03-24 Fred Glover

The margin-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Moreover,…

Computer Vision and Pattern Recognition · Computer Science 2019-12-18 JT Wu , L. Wang

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

Machine Learning · Computer Science 2026-04-13 Matheus Vinícius Todescato , Joel Luís Carbonera

In this paper, we consider the composite optimization problem, where the objective function integrates a continuously differentiable loss function with a nonsmooth regularization term. Moreover, only the function values for the…

Optimization and Control · Mathematics 2024-01-09 Shanglin Liu , Lei Wang , Nachuan Xiao , Xin Liu

We study continual learning on multiple linear classification tasks by sequentially running gradient descent (GD) for a fixed budget of iterations per task. When all tasks are jointly linearly separable and are presented in a cyclic/random…

Machine Learning · Computer Science 2025-04-29 Hyunji Jung , Hanseul Cho , Chulhee Yun

Classic zeroth-order optimization approaches typically optimize for a smoothed version of the original function, i.e., the expected objective under randomly perturbed model parameters. This can be interpreted as encouraging the loss values…

Machine Learning · Computer Science 2025-10-21 Xuchen Gong , Tian Li

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated…

Machine Learning · Computer Science 2020-10-05 Xi Gao , Han Zhang , Aliakbar Panahi , Tom Arodz

Optimization is an important module of modern machine learning applications. Tremendous efforts have been made to accelerate optimization algorithms. A common formulation is achieving a lower loss at a given time. This enables a…

Machine Learning · Computer Science 2025-05-29 Zhonglin Xie , Yiman Fong , Haoran Yuan , Zaiwen Wen

Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between…

Machine Learning · Statistics 2019-05-16 Arthur Mensch , Mathieu Blondel , Gabriel Peyré

In classification, the de facto method for aggregating individual losses is the average loss. When the actual metric of interest is 0-1 loss, it is common to minimize the average surrogate loss for some well-behaved (e.g. convex) surrogate.…

Machine Learning · Computer Science 2018-11-06 Bryan He , James Zou

Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods…

Machine Learning · Computer Science 2022-08-09 David Macêdo , Cleber Zanchettin , Teresa Ludermir

For the binary classification problem, a novel nonlinear kernel-free quadratic hyper-surface support vector machine with 0-1 loss function (QSSVM$_{0/1}$) is proposed. Specifically, the task of QSSVM$_{0/1}$ is to seek a quadratic…

Optimization and Control · Mathematics 2024-04-17 Mingyang Wu , Zhixia Yang , Junyou Ye

Many evaluation metrics can be used to assess the performance of models in binary classification tasks. However, most of them are derived from a confusion matrix in a non-differentiable form, making it very difficult to generate a…

Machine Learning · Computer Science 2024-05-24 Doheon Han , Nuno Moniz , Nitesh V Chawla

Zeroth-order optimization methods are developed to overcome the practical hurdle of having knowledge of explicit derivatives. Instead, these schemes work with merely access to noisy functions evaluations. One of the predominant approaches…

Optimization and Control · Mathematics 2022-08-22 Wouter Jongeneel

This paper proposes a multi-step probabilistic forecasting framework using a single neural-network based model to generate simultaneous point and interval forecasts. Our approach ensures non-crossing prediction intervals (PIs) through a…

Machine Learning · Computer Science 2026-04-21 Worachit Amnuaypongsa , Yotsapat Suparanonrat , Pana Wanitchollakit , Jitkomut Songsiri

This paper addresses the distributed stochastic minimax optimization problem subject to stochastic constraints. We propose a novel first-order Softmax-Weighted Switching Gradient method tailored for federated learning. Under full client…

Machine Learning · Computer Science 2026-03-09 Zhankun Luo , Antesh Upadhyay , Sang Bin Moon , Abolfazl Hashemi

We introduce Goldilocks Selection, a technique for faster model training which selects a sequence of training points that are "just right". We propose an information-theoretic acquisition function -- the reducible validation loss -- and…