English
Related papers

Related papers: Learning and Generalization with Mixture Data

200 papers

Collaborative learning, which enables collaborative and decentralized training of deep neural networks at multiple institutions in a privacy-preserving manner, is rapidly emerging as a valuable technique in healthcare applications. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Liangqiong Qu , Niranjan Balachandar , Miao Zhang , Daniel Rubin

Generalised linear models for multi-class classification problems are one of the fundamental building blocks of modern machine learning tasks. In this manuscript, we characterise the learning of a mixture of $K$ Gaussians with generic means…

A common approach to statistical learning with big-data is to randomly split it among $m$ machines and learn the parameter of interest by averaging the $m$ individual estimates. In this paper, focusing on empirical risk minimization, or…

Machine Learning · Statistics 2016-06-14 Jonathan Rosenblatt , Boaz Nadler

Diffusion models are powerful generative models that produce high-quality samples from complex data. While their infinite-data behavior is well understood, their generalization with finite data remains less clear. Classical learning theory…

Machine Learning · Statistics 2026-02-02 Claudia Merger , Sebastian Goldt

A fundamental question in theoretical machine learning is generalization. Over the past decades, the PAC-Bayesian approach has been established as a flexible framework to address the generalization capabilities of machine learning…

Machine Learning · Computer Science 2024-03-28 Fredrik Hellström , Giuseppe Durisi , Benjamin Guedj , Maxim Raginsky

We study stochastic optimization with data-adaptive sampling schemes to train pairwise learning models. Pairwise learning is ubiquitous, and it covers several popular learning tasks such as ranking, metric learning and AUC maximization. A…

Machine Learning · Computer Science 2025-04-10 Sijia Zhou , Yunwen Lei , Ata Kabán

Problem definition: A key challenge in supervised learning is data scarcity, which can cause prediction models to overfit to the training data and perform poorly out of sample. A contemporary approach to combat overfitting is offered by…

Optimization and Control · Mathematics 2025-10-10 Reza Belbasi , Aras Selvi , Wolfram Wiesemann

How quickly can a given class of concepts be learned from examples? It is common to measure the performance of a supervised machine learning algorithm by plotting its "learning curve", that is, the decay of the error rate as a function of…

Machine Learning · Computer Science 2020-11-10 Olivier Bousquet , Steve Hanneke , Shay Moran , Ramon van Handel , Amir Yehudayoff

Federated learning enables multiple institutions to collaboratively train machine learning models on their local data in a privacy-preserving way. However, its distributed nature often leads to significant heterogeneity in data…

Machine Learning · Computer Science 2021-07-20 Liangqiong Qu , Niranjan Balachandar , Daniel L Rubin

The commonly used latent space embedding techniques, such as Principal Component Analysis, Factor Analysis, and manifold learning techniques, are typically used for learning effective representations of homogeneous data. However, they do…

Machine Learning · Computer Science 2021-10-04 Yasin Yilmaz , Mehmet Aktukmak , Alfred O. Hero

Message passing neural networks (MPNN) have seen a steep rise in popularity since their introduction as generalizations of convolutional neural networks to graph-structured data, and are now considered state-of-the-art tools for solving a…

Machine Learning · Computer Science 2022-08-05 Sohir Maskey , Ron Levie , Yunseok Lee , Gitta Kutyniok

Learning the similarity between images constitutes the foundation for numerous vision tasks. The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes. However, the main…

Computer Vision and Pattern Recognition · Computer Science 2021-09-10 Timo Milbich , Karsten Roth , Biagio Brattoli , Björn Ommer

Pretraining data of large language models composes multiple domains (e.g., web texts, academic papers, codes), whose mixture proportions crucially impact the competence of outcome models. While existing endeavors rely on heuristics or…

Computation and Language · Computer Science 2025-03-21 Jiasheng Ye , Peiju Liu , Tianxiang Sun , Jun Zhan , Yunhua Zhou , Xipeng Qiu

Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a combinatorially large number of novel data? What signal in the…

Machine Learning · Statistics 2025-06-05 Alessandro Favero , Antonio Sclocchi , Francesco Cagnetta , Pascal Frossard , Matthieu Wyart

Symmetries are known to improve the empirical performance of machine learning models, yet theoretical guarantees explaining these gains remain limited. Prior work has focused mainly on compact group symmetries and often assumes that the…

Machine Learning · Computer Science 2025-10-21 Armin Beck , Peter Ochs

We consider the problem of PAC-learning from distributed data and analyze fundamental communication complexity questions involved. We provide general upper and lower bounds on the amount of communication needed to learn well, showing that…

Machine Learning · Computer Science 2012-05-28 Maria-Florina Balcan , Avrim Blum , Shai Fine , Yishay Mansour

Ensembles, as a widely used and effective technique in the machine learning community, succeed within a key element -- "diversity." The relationship between diversity and generalization, unfortunately, is not entirely understood and remains…

Machine Learning · Computer Science 2021-05-10 Yijun Bian , Huanhuan Chen

We propose the online machine learning for big data analysis with heterogeneity. We performed an experiment to compare the accuracy of each iteration between batch one and online one. It is possible to converge quickly with the same…

Machine Learning · Computer Science 2019-06-20 Kazuki Seshimo , Ota Akira , Nishio Daichi , Yamane Satoshi

Large-scale data analysis poses both statistical and computational problems which need to be addressed simultaneously. A solution is often straightforward if the data are homogeneous: one can use classical ideas of subsampling and mean…

Methodology · Statistics 2014-09-10 Peter Bühlmann , Nicolai Meinshausen

Statistical learning theory provides bounds of the generalization gap, using in particular the Vapnik-Chervonenkis dimension and the Rademacher complexity. An alternative approach, mainly studied in the statistical physics literature, is…

Disordered Systems and Neural Networks · Physics 2020-09-04 Alia Abbara , Benjamin Aubin , Florent Krzakala , Lenka Zdeborová