English
Related papers

Related papers: Functional Dimensional Regularization for O(N) Mod…

200 papers

Density functional theory (DFT) offers a desirable balance between quantitative accuracy and computational efficiency in practical many-electron calculations. Its central component, the exchange-correlation energy functional, has been…

Neural Radiance Fields (NeRF) has emerged as a compelling framework for scene representation and 3D recovery. To improve its performance on real-world data, depth regularizations have proven to be the most effective ones. However, depth…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Aoxiang Fan , Corentin Dumery , Nicolas Talabot , Pascal Fua

Quadratic regression (QR) models naturally extend linear models by considering interaction effects between the covariates. To conduct model selection in QR, it is important to maintain the hierarchical model structure between main effects…

Methodology · Statistics 2016-07-15 Ning Hao , Yang Feng , Hao Helen Zhang

We introduce a new class of non-linear function-on-function regression models for functional data using neural networks. We propose a framework using a hidden layer consisting of continuous neurons, called a continuous hidden layer, for…

Methodology · Statistics 2023-10-10 Aniruddha Rajendra Rao , Matthew Reimherr

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may…

Machine Learning · Computer Science 2026-05-15 Yuxin Guo , Yihao Yue , Yunhao Ni , Yizhou Ruan , Jie Luo , Wenjun Wu , Lei Huang

The statistical problem of estimating the effective dimension-reduction (EDR) subspace in the multi-index regression model with deterministic design and additive noise is considered. A new procedure for recovering the directions of the EDR…

Statistics Theory · Mathematics 2007-06-13 Arnak Dalalyan , Anatoly Juditsky , Vladimir Spokoiny

Recently, deep learning has been widely applied in functional data analysis (FDA) with notable empirical success. However, the infinite dimensionality of functional data necessitates an effective dimension reduction approach for functional…

Machine Learning · Statistics 2025-05-13 Zhongjie Shi , Jun Fan , Linhao Song , Ding-Xuan Zhou , Johan A. K. Suykens

Fractional-order stochastic gradient descent (FOSGD) leverages fractional exponents to capture long-memory effects in optimization. However, its utility is often limited by the difficulty of tuning and stabilizing these exponents. We…

Machine Learning · Computer Science 2025-05-09 Mohammad Partohaghighi , Roummel Marcia , YangQuan Chen

The functional flow equations for the Legendre effective action, with respect to changes in a smooth cutoff, are approximated by a derivative expansion; no other approximation is made. This results in a set of coupled non-linear…

High Energy Physics - Phenomenology · Physics 2009-10-28 Tim R. Morris

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

Machine Learning · Computer Science 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

We introduce a novel discretization technique for both elliptic and parabolic fractional diffusion problems based on double exponential quadrature formulas and the Riesz-Dunford functional calculus. Compared to related schemes, the new…

Numerical Analysis · Mathematics 2020-12-11 Alexander Rieder

Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this…

Graphics · Computer Science 2025-05-15 Liwen Wu , Sai Bi , Zexiang Xu , Hao Tan , Kai Zhang , Fujun Luan , Haolin Lu , Ravi Ramamoorthi

We apply the nonperturbative functional renormalization group (NP-FRG) in the superfield formalism that we have developed in the preceding paper to study long-standing issues concerning the critical behavior of the random field Ising model.…

Statistical Mechanics · Physics 2013-05-30 Matthieu Tissier , Gilles Tarjus

The simulation of quantum field theories, both classical and quantum, requires regularization of infinitely many degrees of freedom. However, in the context of field digitization (FD) -- a truncation of the local fields to $N$ discrete…

Quantum Physics · Physics 2026-03-05 Gabriele Calliari , Robert Ott , Hannes Pichler , Torsten V. Zache

We extend an implicit regularization scheme to be applicable in the $n$-dimensional space-time. Within this scheme divergences involving parity violating objects can be consistently treated without recoursing to dimensional continuation.…

High Energy Physics - Theory · Physics 2016-09-06 A. P. B. Scarpelli , M. Sampaio , M. C. Nemes

Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while detecting Out-of-Distribution (OOD) inputs as they directly…

Machine Learning · Computer Science 2021-11-17 Nishant Kumar , Pia Hanfeld , Michael Hecht , Michael Bussmann , Stefan Gumhold , Nico Hoffmann

Symmetric nonnegative matrix factorization (NMF), a special but important class of the general NMF, is demonstrated to be useful for data analysis and in particular for various clustering tasks. Unfortunately, designing fast algorithms for…

Machine Learning · Computer Science 2018-11-15 Zhihui Zhu , Xiao Li , Kai Liu , Qiuwei Li

Density Functional Theory (DFT) is widely used for atomistic simulations. However, its reach stays limited due to several limitations such as lack of accurate exchange-correlation functional, requirement of costly O(N 3) diagonalization…

Quantum Physics · Physics 2026-05-18 Namrata Manglani , Samrit Kumar Maity , Shashank Sharma , Soham Phulare , Sanjay Wandhekar

We apply pseudo-spectral methods to construct global solutions of functional renormalisation group equations in field space to high accuracy. For this, we introduce a basis to resolve both finite as well as asymptotic regions of effective…

High Energy Physics - Theory · Physics 2015-09-03 Julia Borchardt , Benjamin Knorr

I review the current status of FDR, the recently introduced Four-Dimensional Regularization/Renormalization approach to ultraviolet divergences in Quantum Field Theory. FDR also regulates infrared and collinear infinities in the…

High Energy Physics - Phenomenology · Physics 2013-04-24 Roberto Pittau