English
Related papers

Related papers: Consistent optimization of AMS by logistic loss mi…

200 papers

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case…

Various evaluation measures have been developed for multi-label classification, including Hamming Loss (HL), Subset Accuracy (SA) and Ranking Loss (RL). However, there is a gap between empirical results and the existing theories: 1) an…

Machine Learning · Computer Science 2020-11-17 Guoqiang Wu , Jun Zhu

This letter proposes a novel sparsity-aware adaptive filtering scheme and algorithms based on an alternating optimization strategy with shrinkage. The proposed scheme employs a two-stage structure that consists of an alternating…

Systems and Control · Computer Science 2023-07-19 Rodrigo C. de Lamare , Raimundo Sampaio-Neto

Despite achieving great success, Deep Neural Networks (DNNs) are vulnerable to adversarial examples. How to accurately evaluate the adversarial robustness of DNNs is critical for their deployment in real-world applications. An ideal…

Machine Learning · Computer Science 2022-04-12 Pengfei Xia , Ziqiang Li , Bin Li

In a typical optimization problem, the task is to pick one of a number of options with the lowest cost or the highest value. In practice, these cost/value quantities often come through processes such as measurement or machine learning,…

Data Structures and Algorithms · Computer Science 2022-07-20 Mohammad Mahdian , Jieming Mao , Kangning Wang

This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. To…

Machine Learning · Computer Science 2024-07-19 Wanyun Xie , Fabian Latorre , Kimon Antonakopoulos , Thomas Pethick , Volkan Cevher

The maximum likelihood estimation is computationally demanding for large datasets, particularly when the likelihood function includes integrals. Subsampling can reduce the computational burden, but it often results in efficiency loss.This…

Methodology · Statistics 2026-04-27 Miaomiao Su , Qihua Wang , Ruoyu Wang

A learning algorithm referred to as Maximum Margin (MM) is proposed for considering the class-imbalance data learning issue: the trained model tends to predict the majority of classes rather than the minority ones. That is, underfitting for…

Machine Learning · Computer Science 2023-03-30 Haeyong Kang , Thang Vu , Chang D. Yoo

Based on the stochastic maximum principle for the partially coupled forward-backward stochastic control system (FBSCS for short), a modified method of successive approximations (MSA for short) is established for stochastic recursive optimal…

Optimization and Control · Mathematics 2022-01-11 Shaolin Ji , Rundong Xu

Sharpness-Aware Minimization (SAM) is an optimization technique designed to improve generalization by favoring flatter loss minima. To achieve this, SAM optimizes a modified objective that penalizes sharpness, using computationally…

Machine Learning · Computer Science 2024-11-05 Nalin Tiwary , Siddarth Aananth

A Regret Minimizing Set (RMS) is a useful concept in which a smaller subset of a database is selected while mostly preserving the best scores along every possible utility function. In this paper, we study the $k$-Regret Minimizing Sets…

Databases · Computer Science 2022-01-19 Phoomraphee Luenam , Yau Pun Chen , Raymond Chi-Wing Wong

The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise optimization, which treats each transformer block as a single…

Machine Learning · Computer Science 2026-01-15 Yuxi Liu , Renjia Deng , Yutong He , Xue Wang , Tao Yao , Kun Yuan

We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks. It can be viewed as an Adam optimizer with theoretically supported, adaptive learning-rate decay and weight decay. A key insight behind Amos…

Machine Learning · Computer Science 2022-11-22 Ran Tian , Ankur P. Parikh

Theoretical results show that Bayesian methods can achieve lower bounds on regret for online logistic regression. In practice, however, such techniques may not be feasible especially for very large feature sets. Various approximations that,…

Machine Learning · Computer Science 2021-01-29 Gil I. Shamir , Wojciech Szpankowski

Meta-learning synthesizes and leverages the knowledge from a given set of tasks to rapidly learn new tasks using very little data. Meta-learning of linear regression tasks, where the regressors lie in a low-dimensional subspace, is an…

Machine Learning · Computer Science 2021-05-19 Kiran Koshy Thekumparampil , Prateek Jain , Praneeth Netrapalli , Sewoong Oh

We present $\alpha$-loss, $\alpha \in [1,\infty]$, a tunable loss function for binary classification that bridges log-loss ($\alpha=1$) and $0$-$1$ loss ($\alpha = \infty$). We prove that $\alpha$-loss has an equivalent margin-based form…

Machine Learning · Computer Science 2019-03-21 Tyler Sypherd , Mario Diaz , Lalitha Sankar , Peter Kairouz

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 study the regret of simulated annealing (SA) based approaches to solving discrete stochastic optimization problems. The main theoretical conclusion is that the regret of the simulated annealing algorithm, with either noisy or noiseless…

Optimization and Control · Mathematics 2021-03-29 Suhail M. Shah

Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters. Appropriately scheduling the optimization of a task objective or a set of parameters is…

Machine Learning · Computer Science 2018-10-08 Haowen Xu , Hao Zhang , Zhiting Hu , Xiaodan Liang , Ruslan Salakhutdinov , Eric Xing

Affine rank minimization algorithms typically rely on calculating the gradient of a data error followed by a singular value decomposition at every iteration. Because these two steps are expensive, heuristic approximations are often used to…

Optimization and Control · Mathematics 2013-06-04 Stephen Becker , Volkan Cevher , Anastasios Kyrillidis