English
Related papers

Related papers: The Sample Complexity of Multi-Distribution Learni…

200 papers

We initiate the study of a new notion of adversarial loss which we call distributional adversarial loss. In this notion, we assume for each original example, the allowed adversarial perturbation set is a family of distributions, and the…

Machine Learning · Computer Science 2025-06-23 Saba Ahmadi , Siddharth Bhandari , Avrim Blum , Chen Dan , Prabhav Jain

How many bits of information are revealed by a learning algorithm for a concept class of VC-dimension $d$? Previous works have shown that even for $d=1$ the amount of information may be unbounded (tend to $\infty$ with the universe size).…

Machine Learning · Computer Science 2018-11-27 Ido Nachum , Amir Yehudayoff

This work considers the sample complexity of obtaining an $\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating,…

Machine Learning · Computer Science 2022-12-02 Jinghan Wang , Mengdi Wang , Lin F. Yang

We study a generalization of boosting to the multiclass setting. We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being "slightly better than random guessing". We…

Machine Learning · Computer Science 2023-07-04 Nataly Brukhim , Amit Daniely , Yishay Mansour , Shay Moran

We study the fundamental limits to communication-efficient distributed methods for convex learning and optimization, under different assumptions on the information available to individual machines, and the types of functions considered. We…

Machine Learning · Computer Science 2015-10-29 Yossi Arjevani , Ohad Shamir

The classical PAC sample complexity bounds are stated for any Empirical Risk Minimizer (ERM) and contain an extra logarithmic factor $\log(1/{\epsilon})$ which is known to be necessary for ERM in general. It has been recently shown by…

Machine Learning · Computer Science 2020-05-26 Olivier Bousquet , Steve Hanneke , Shay Moran , Nikita Zhivotovskiy

We study a fundamental question of domain generalization: given a family of domains (i.e., data distributions), how many randomly sampled domains do we need to collect data from in order to learn a model that performs reasonably well on…

Machine Learning · Computer Science 2025-10-27 Cynthia Dwork , Lunjia Hu , Han Shao

The capability of reliably detecting out-of-distribution samples is one of the key factors in deploying a good classifier, as the test distribution always does not match with the training distribution in most real-world applications. In…

Machine Learning · Computer Science 2021-04-05 Dongha Lee , Sehun Yu , Hwanjo Yu

Learning from a limited number of samples is challenging since the learned model can easily become overfitted based on the biased distribution formed by only a few training examples. In this paper, we calibrate the distribution of these…

Machine Learning · Computer Science 2021-08-17 Shuo Yang , Lu Liu , Min Xu

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over…

In scientific machine learning, models are routinely deployed with parameter values or boundary conditions far from those used in training. This paper studies the learning-where-to-learn problem of designing a training data distribution…

Machine Learning · Computer Science 2025-12-09 Nicolas Guerra , Nicholas H. Nelsen , Yunan Yang

The deployment of machine learning solutions in real-world scenarios often involves addressing the challenge of out-of-distribution (OOD) detection. While significant efforts have been devoted to OOD detection in classical supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Loïc Le Bescond , Maria Vakalopoulou , Stergios Christodoulidis , Fabrice André , Hugues Talbot

Machine learning algorithms often encounter different or "out-of-distribution" (OOD) data at deployment time, and OOD detection is frequently employed to detect these examples. While it works reasonably well in practice, existing…

Machine Learning · Computer Science 2025-01-16 Konstantin Garov , Kamalika Chaudhuri

The PAC-Bayesian framework has significantly advanced the understanding of statistical learning, particularly for majority voting methods. Despite its successes, its application to multi-view learning -- a setting with multiple…

Machine Learning · Computer Science 2025-10-15 Mehdi Hennequin , Abdelkrim Zitouni , Khalid Benabdeslem , Haytham Elghazel , Yacine Gaci

Domain adaptation is transfer learning which aims to generalize a learning model across training and testing data with different distributions. Most previous research tackle this problem in seeking a shared feature representation between…

Machine Learning · Computer Science 2017-04-17 Lingkun Luo , Xiaofang Wang , Shiqiang Hu , Chao Wang , Yuxing Tang , Liming Chen

We generalize the PAC (probably approximately correct) learning model to the quantum world by generalizing the concepts from classical functions to quantum processes, defining the problem of \emph{PAC learning quantum process}, and study…

Quantum Physics · Physics 2021-05-20 Kai-Min Chung , Han-Hsuan Lin

We consider learning under the constraint of local differential privacy (LDP). For many learning problems known efficient algorithms in this model require many rounds of communication between the server and the clients holding the data…

Machine Learning · Computer Science 2019-10-29 Amit Daniely , Vitaly Feldman

We study binary classification algorithms for which the prediction on any point is not too sensitive to individual examples in the dataset. Specifically, we consider the notions of uniform stability (Bousquet and Elisseeff, 2001) and…

Machine Learning · Computer Science 2020-09-24 Yuval Dagan , Vitaly Feldman

Many dynamic decision problems, such as robotic control, involve a series of tasks, many of which are unknown at training time. Typical approaches for these problems, such as multi-task and meta reinforcement learning, do not generalize…

Machine Learning · Computer Science 2025-05-28 Luise Ge , Michael Lanier , Anindya Sarkar , Bengisu Guresti , Chongjie Zhang , Yevgeniy Vorobeychik

We compute the transition probability between two learning tasks, and show that it decomposes into two factors. The first depends on the geometry of the loss landscape of a model trained on each task, independent of any particular model…

Machine Learning · Computer Science 2019-05-30 Alessandro Achille , Glen Mbeng , Stefano Soatto