English
Related papers

Related papers: Information-Geometric Decomposition of Generalizat…

200 papers

We introduce an information-theoretic framework that uses variational autoencoders (VAEs) to extract compact, physically interpretable manifolds from high-dimensional flow-field data. To this end, the Kullback--Leibler (KL) divergence in…

Fluid Dynamics · Physics 2026-04-21 Zhiyuan Wang , Iacopo Tirelli , Stefano Discetti , Andrea Ianiro

Finding the optimal model complexity that minimizes the generalization error (GE) is a key issue of machine learning. For the conventional supervised learning, this task typically involves the bias-variance tradeoff: lowering the bias by…

Statistical Mechanics · Physics 2023-09-13 Gilhan Kim , Hojun Lee , Junghyo Jo , Yongjoo Baek

Since its introduction, the partial information decomposition (PID) has emerged as a powerful, information-theoretic technique useful for studying the structure of (potentially higher-order) interactions in complex systems. Despite its…

Information Theory · Computer Science 2023-12-11 Thomas F. Varley

When we consider discretization of continuous probability distributions, it inevitably induces irreversible geometric distortion of local measure on the discretized support. While such discretziation-induced distortion is extrinsic to…

Statistical Mechanics · Physics 2026-05-28 Koretaka Yuge

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE)…

Machine Learning · Computer Science 2025-03-12 Jiequan Cui , Beier Zhu , Qingshan Xu , Zhuotao Tian , Xiaojuan Qi , Bei Yu , Hanwang Zhang , Richang Hong

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE)…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Jiequan Cui , Zhuotao Tian , Zhisheng Zhong , Xiaojuan Qi , Bei Yu , Hanwang Zhang

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

We propose a unified information-geometric framework that formalizes understanding in learning as a trade-off between informativeness and geometric simplicity. An encoder phi is evaluated by U(phi) = I(phi(X); Y) - beta * C(phi), where…

Machine Learning · Computer Science 2025-11-05 Ronald Katende

The $\beta$-VAE is a foundational framework for unsupervised disentanglement, using $\beta$ to regulate the trade-off between latent factorization and reconstruction fidelity. Empirically, however, disentanglement performance exhibits a…

Machine Learning · Statistics 2026-02-11 Minh Vu , Xiaoliang Wan , Shuangqing Wei

The Kullback-Leibler (KL) divergence is a foundational measure for comparing probability distributions. Yet in multivariate settings, its single value often obscures the underlying reasons for divergence, conflating mismatches in individual…

Other Computer Science · Computer Science 2025-05-06 William Cook

While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present…

Machine Learning · Computer Science 2025-05-27 Futoshi Futami , Masahiro Fujisawa

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

Meta-analytic methods tend to take all-or-nothing approaches to study-level heterogeneity, assuming all studies are heterogeneous or homogeneous, leading to inefficiency and/or bias in estimation and inference. In this paper, we develop a…

Methodology · Statistics 2026-03-12 Elizabeth M. Davis , Emily C. Hector

Modern computational models in supervised machine learning are often highly parameterized universal approximators. As such, the value of the parameters is unimportant, and only the out of sample performance is considered. On the other hand…

Computation · Statistics 2021-11-04 Matthew Dixon , Tyler Ward

Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in…

Computation and Language · Computer Science 2023-05-12 Lingzhi Wang , Tong Chen , Wei Yuan , Xingshan Zeng , Kam-Fai Wong , Hongzhi Yin

Variational Autoencoders (VAEs) have become a cornerstone in generative modeling and representation learning within machine learning. This paper explores a nuanced aspect of VAEs, focusing on interpreting the Kullback-Leibler (KL)…

Machine Learning · Computer Science 2024-06-25 Mariano Rivera

A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that…

Statistics Theory · Mathematics 2025-06-04 Mark K. Transtrum , Gus L. W. Hart , Tyler J. Jarvis , Jared P. Whitehead

Dimensionality reduction is critical across various domains of science including neuroscience. Probabilistic Principal Component Analysis (PPCA) is a prominent dimensionality reduction method that provides a probabilistic approach unlike…

Machine Learning · Computer Science 2025-09-24 Han-Lin Hsieh , Maryam M. Shanechi

High-dimensional data often exhibit dependencies among variables that violate the isotropic-noise assumption under which principal component analysis (PCA) is optimal. For cases where the noise is not independent and identically distributed…

Machine Learning · Computer Science 2026-01-16 Antonio Briola , Marwin Schmidt , Fabio Caccioli , Carlos Ros Perez , James Singleton , Christian Michler , Tomaso Aste

Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce Uncertainty-Guided Inference-Time Selection, a lightweight…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Divake Kumar , Patrick Poggi , Sina Tayebati , Devashri Naik , Nilesh Ahuja , Amit Ranjan Trivedi
‹ Prev 1 2 3 10 Next ›