English
Related papers

Related papers: A solvable high-dimensional model where nonlinear …

200 papers

Unsupervised representation learning seeks to recover latent generative factors, yet standard methods relying on statistical independence often fail to capture causal dependencies. A central challenge is identifiability: as established in…

Machine Learning · Computer Science 2025-12-30 Hans Jarett J. Ong , Brian Godwin S. Lim , Dominic Dayta , Renzo Roel P. Tan , Kazushi Ikeda

We study attention mechanisms through the lens of a canonical unsupervised problem: principal component analysis (PCA). We show that, when trained on Gaussian data, both softmax and linear attention layers learn parameters that align with…

Optimization and Control · Mathematics 2026-05-19 Rodrigo Maulen-Soto , Claire Boyer

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be…

Machine Learning · Statistics 2025-06-02 Stas Syrota , Yevgen Zainchkovskyy , Johnny Xi , Benjamin Bloem-Reddy , Søren Hauberg

Suppose we observe data of the form $Y_i = D_i (S_i + \varepsilon_i) \in \mathbb{R}^p$ or $Y_i = D_i S_i + \varepsilon_i \in \mathbb{R}^p$, $i=1,\ldots,n$, where $D_i \in \mathbb{R}^{p\times p}$ are known diagonal matrices, $\varepsilon_i$…

Statistics Theory · Mathematics 2018-11-05 Edgar Dobriban , William Leeb , Amit Singer

Recent work suggests that convolutional neural networks of different architectures learn to classify images in the same order. To understand this phenomenon, we revisit the over-parametrized deep linear network model. Our analysis reveals…

Machine Learning · Computer Science 2023-12-29 Guy Hacohen , Daphna Weinshall

This article establishes a new and comprehensive estimation and inference theory for principal component analysis (PCA) under the weak factor model that allow for cross-sectional dependent idiosyncratic components under the nearly minimal…

Methodology · Statistics 2024-10-02 Jianqing Fan , Yuling Yan , Yuheng Zheng

To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations often exhibit a high-dimensional and strongly nonlinear…

Machine Learning · Computer Science 2025-03-04 Lorenzo Basile , Santiago Acevedo , Luca Bortolussi , Fabio Anselmi , Alex Rodriguez

Identifiability of statistical models is a key notion in unsupervised representation learning. Recent work of nonlinear independent component analysis (ICA) employs auxiliary data and has established identifiable conditions. This paper…

Machine Learning · Statistics 2024-05-31 Hiroaki Sasaki

Autoencoders are the simplest neural network for unsupervised learning, and thus an ideal framework for studying feature learning. While a detailed understanding of the dynamics of linear autoencoders has recently been obtained, the study…

Machine Learning · Statistics 2022-08-01 Maria Refinetti , Sebastian Goldt

An old problem in multivariate statistics is that linear Gaussian models are often unidentifiable, i.e. some parameters cannot be uniquely estimated. In factor (component) analysis, an orthogonal rotation of the factors is unidentifiable,…

Machine Learning · Statistics 2023-05-04 Aapo Hyvärinen , Ilyes Khemakhem , Ricardo Monti

Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies…

The framework of variational autoencoders allows us to efficiently learn deep latent-variable models, such that the model's marginal distribution over observed variables fits the data. Often, we're interested in going a step further, and…

Machine Learning · Statistics 2020-12-22 Ilyes Khemakhem , Diederik P. Kingma , Ricardo Pio Monti , Aapo Hyvärinen

Loss curves are smooth during most of model training, so visible discontinuities stand out as possible conceptual breakthroughs. Studying these breakthroughs enables a deeper understanding of learning dynamics, but only when they are…

Machine Learning · Computer Science 2026-03-23 Sara Kangaslahti , Elan Rosenfeld , Naomi Saphra

Linear discriminant analysis (LDA) is a typical method for classification problems with large dimensions and small samples. There are various types of LDA methods that are based on the different types of estimators for the covariance…

Methodology · Statistics 2023-03-07 Jaehoan Kim , Hoyoung Park , Junyong Park

Modern network data analysis often involves analyzing network structures alongside covariate features to gain deeper insights into underlying patterns. However, traditional covariate-assisted statistical network models may not adequately…

Methodology · Statistics 2025-05-07 Peng Zhao , Yabo Niu

Identifying latent variables and causal structures from observational data is essential to many real-world applications involving biological data, medical data, and unstructured data such as images and languages. However, this task can be…

Machine Learning · Computer Science 2023-11-01 Lingjing Kong , Biwei Huang , Feng Xie , Eric Xing , Yuejie Chi , Kun Zhang

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

Regression models with both high-dimensional responses and covariates have attracted growing attention. Standard multivariate regression models become inadequate when the response variables depend not only on observed covariates but also on…

Methodology · Statistics 2026-05-01 Jing Ouyang , Chengyu Cui , Yunxiao Chen , Kean Ming Tan , Gongjun Xu

Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low effective due to the straightforward encoder-decoder…

Machine Learning · Computer Science 2018-04-13 Jiangchao Yao , Ivor Tsang , Ya Zhang

Principal component analysis (PCA) is arguably the most widely used approach for large-dimensional factor analysis. While it is effective when the factors are sufficiently strong, it can be inconsistent when the factors are weak and/or the…

Methodology · Statistics 2025-08-22 Zhongyuan Lyu , Ming Yuan
‹ Prev 1 3 4 5 6 7 10 Next ›