English
Related papers

Related papers: Calibrated Surrogate Losses for Adversarially Robu…

200 papers

This paper aims to understand whether machine learning models should be trained using cost-sensitive surrogates or cost-agnostic ones (e.g., cross-entropy). Analyzing this question through the lens of $\mathcal{H}$-calibration, we find that…

Machine Learning · Computer Science 2025-02-28 Sanket Shah , Milind Tambe , Jessie Finocchiaro

We present a new machine learning approach to estimate personalized treatment effects in the classical potential outcomes framework with binary outcomes. To overcome the problem that both treatment and control outcomes for the same unit are…

Machine Learning · Statistics 2018-05-07 Siong Thye Goh , Cynthia Rudin

The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability. While many deep neural networks have shown impressive performance in terms of predictive accuracy, it has been shown that…

Machine Learning · Computer Science 2021-06-28 Sadia Chowdhury , Ruth Urner

Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objective is to produce a…

Statistics Theory · Mathematics 2019-11-14 Steve Hanneke , Liu Yang

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many…

Machine Learning · Computer Science 2022-06-30 Jessie Finocchiaro , Rafael M. Frongillo , Bo Waggoner

Supervised classification techniques use training samples to find classification rules with small expected 0-1 loss. Conventional methods achieve efficient learning and out-of-sample generalization by minimizing surrogate losses over…

Machine Learning · Statistics 2021-08-12 Santiago Mazuelas , Andrea Zanoni , Aritz Perez

Consider a classification problem where we have both labeled and unlabeled data available. We show that for linear classifiers defined by convex margin-based surrogate losses that are decreasing, it is impossible to construct any…

Machine Learning · Statistics 2019-01-09 Jesse H. Krijthe , Marco Loog

Despite tremendous advancements of machine learning models and algorithms in various application domains, they are known to be vulnerable to subtle, natural or intentionally crafted perturbations in future input data, known as adversarial…

Machine Learning · Statistics 2025-06-03 Jingfu Peng , Yuhong Yang

We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surrogates. We pose the training problem as an optimization over a…

Machine Learning · Computer Science 2020-02-21 Qijia Jiang , Olaoluwa Adigun , Harikrishna Narasimhan , Mahdi Milani Fard , Maya Gupta

Adversarial training can be used to learn models that are robust against perturbations. For linear models, it can be formulated as a convex optimization problem. Compared to methods proposed in the context of deep learning, leveraging the…

Machine Learning · Statistics 2025-03-20 Antônio H. RIbeiro , Thomas B. Schön , Dave Zahariah , Francis Bach

Stochastic inverse problems are generally solved by some form of finite sampling of a space of uncertain parameters. For computationally expensive models, surrogate response surfaces are often employed to increase the number of samples used…

Numerical Analysis · Mathematics 2018-07-04 Steven Mattis , Barbara Wohlmuth

We consider the problem of learning support vector machines robust to uncertainty. It has been established in the literature that typical loss functions, including the hinge loss, are sensible to data perturbations and outliers, thus…

Machine Learning · Computer Science 2024-02-06 Valentina Cepeda , Andrés Gómez , Shaoning Han

Adversarial robustness has become a fundamental requirement in modern machine learning applications. Yet, there has been surprisingly little statistical understanding so far. In this paper, we provide the first result of the optimal minimax…

Machine Learning · Statistics 2020-07-01 Chen Dan , Yuting Wei , Pradeep Ravikumar

Finding classifiers robust to adversarial examples is critical for their safe deployment. Determining the robustness of the best possible classifier under a given threat model for a given data distribution and comparing it to that achieved…

Machine Learning · Computer Science 2023-12-08 Sihui Dai , Wenxin Ding , Arjun Nitin Bhagoji , Daniel Cullina , Ben Y. Zhao , Haitao Zheng , Prateek Mittal

Supervised classification techniques use training samples to learn a classification rule with small expected 0-1 loss (error probability). Conventional methods enable tractable learning and provide out-of-sample generalization by using…

Machine Learning · Statistics 2023-08-21 Santiago Mazuelas , Mauricio Romero , Peter Grünwald

PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with respect to a chosen…

Machine Learning · Statistics 2024-08-19 The Tien Mai

Recent works have shown that the input domain of any machine learning classifier is bound to contain adversarial examples. Thus we can no longer hope to immune classifiers against adversarial examples and instead can only aim to achieve the…

Machine Learning · Computer Science 2020-09-25 Gil Fidel , Ron Bitton , Ziv Katzir , Asaf Shabtai

While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test data might not be…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Tejas Gokhale , Rushil Anirudh , Bhavya Kailkhura , Jayaraman J. Thiagarajan , Chitta Baral , Yezhou Yang

Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shift. We study the robustness of split conformal prediction…

Machine Learning · Statistics 2025-12-23 Xunlei Qian , Yue Xing

Enabling machine learning classifiers to defer their decision to a downstream expert when the expert is more accurate will ensure improved safety and performance. This objective can be achieved with the learning-to-defer framework which…

Machine Learning · Computer Science 2023-11-03 Yuzhou Cao , Hussein Mozannar , Lei Feng , Hongxin Wei , Bo An