English
Related papers

Related papers: FAVOR#: Sharp Attention Kernel Approximations via …

200 papers

Kernel quadrature is widely used to approximate integrals of smooth functions, with worst-case error typically decaying at the minimax rate $n^{-\alpha/d}$ for smoothness $\alpha$ in dimension $d$. Existing rate-optimal methods often depend…

Computation · Statistics 2026-05-19 Edoardo Bandoni , Christian Robert , Julien Stoehr

Transformers are a class of autoregressive deep learning architectures which have recently achieved state-of-the-art performance in various vision, language, and robotics tasks. We revisit the problem of Kalman Filtering in linear dynamical…

Machine Learning · Computer Science 2024-05-21 Gautam Goel , Peter Bartlett

This paper investigates the approximation of Gaussian random variables in Banach spaces, focusing on the high-probability bounds for the approximation of Gaussian random variables using finitely many observations. We derive non-asymptotic…

Statistics Theory · Mathematics 2025-08-28 Daniel Winkle , Ingo Steinwart , Bernard Haasdonk

While the Transformer architecture has achieved remarkable success across various domains, a thorough theoretical foundation explaining its optimization dynamics is yet to be fully developed. In this study, we aim to bridge this…

Machine Learning · Computer Science 2024-11-13 Bingqing Song , Boran Han , Shuai Zhang , Jie Ding , Mingyi Hong

Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint. For neural networks, prior methods, including those based on $\ell_1$…

Machine Learning · Computer Science 2024-06-19 Taisuke Yasuda , MohammadHossein Bateni , Lin Chen , Matthew Fahrbach , Gang Fu , Vahab Mirrokni

Transformers have achieved remarkable performance in a myriad of fields including natural language processing and computer vision. However, when it comes to the graph mining area, where graph neural network (GNN) has been the dominant…

Machine Learning · Computer Science 2021-10-26 Jianan Zhao , Chaozhuo Li , Qianlong Wen , Yiqi Wang , Yuming Liu , Hao Sun , Xing Xie , Yanfang Ye

Randomized algorithms exploit stochasticity to reduce computational complexity. One important example is random feature regression (RFR) that accelerates Gaussian process regression (GPR). RFR approximates an unknown function with a random…

Machine Learning · Computer Science 2025-02-26 Oliver R. A. Dunbar , Nicholas H. Nelsen , Maya Mutic

Robust parameter estimation is a crucial task in several 3D computer vision pipelines such as Structure from Motion (SfM). State-of-the-art algorithms for robust estimation, however, still suffer from difficulties in converging to…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Huu Le , Christopher Zach

Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces. To scale up these methods, we extend the…

Machine Learning · Computer Science 2018-05-25 Romain Brault , Florence d'Alché-Buc , Markus Heinonen

We present a simple and intuitive Focus-and-eXpand (\fax) method to guide the training process of a neural network towards a specific solution. Optimizing a neural network is a highly non-convex problem. Typically, the space of solutions is…

Machine Learning · Computer Science 2020-07-16 Moab Arar , Noa Fish , Dani Daniel , Evgeny Tenetov , Ariel Shamir , Amit Bermano

Gaussian variational approximation is a popular methodology to approximate posterior distributions in Bayesian inference especially in high dimensional and large data settings. To control the computational cost while being able to capture…

Machine Learning · Computer Science 2021-04-07 Bingxin Zhou , Junbin Gao , Minh-Ngoc Tran , Richard Gerlach

Self-attention networks have shown remarkable progress in computer vision tasks such as image classification. The main benefit of the self-attention mechanism is the ability to capture long-range feature interactions in attention-maps.…

Computer Vision and Pattern Recognition · Computer Science 2021-03-19 Andong Tan , Duc Tam Nguyen , Maximilian Dax , Matthias Nießner , Thomas Brox

Compared with voxel-based grid prediction, in the field of 3D semantic occupation prediction for autonomous driving, GaussianFormer proposed using 3D Gaussian to describe scenes with sparse 3D semantic Gaussian based on objects is another…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Ziyue Zhao , Qining Qi , Jianfa Ma

Factorization machines (FM) are a popular model class to learn pairwise interactions by a low-rank approximation. Different from existing FM-based approaches which use a fixed rank for all features, this paper proposes a Rank-Aware FM…

Machine Learning · Computer Science 2019-05-21 Xiaoshuang Chen , Yin Zheng , Jiaxing Wang , Wenye Ma , Junzhou Huang

In the context of Gaussian conditioning, greedy algorithms iteratively select the most informative measurements, given an observed Gaussian random variable. However, the convergence analysis for conditioning Gaussian random variables…

Statistics Theory · Mathematics 2025-02-18 Daniel Winkle , Ingo Steinwart , Bernard Haasdonk

Variable selection for Gaussian process models is often done using automatic relevance determination, which uses the inverse length-scale parameter of each input variable as a proxy for variable relevance. This implicitly determined…

Methodology · Statistics 2019-04-24 Topi Paananen , Juho Piironen , Michael Riis Andersen , Aki Vehtari

Kernel methods are versatile tools for function approximation and surrogate modeling. In particular, greedy techniques offer computational efficiency and reliability through inherent sparsity and provable convergence. Inspired by the…

Numerical Analysis · Mathematics 2026-03-09 Marian Klink , Tobias Ehring , Robin Herkert , Robin Lautenschlager , Dominik Göddeke , Bernard Haasdonk

We show how the notion of message passing can be used to streamline the algebra and computer coding for fast approximate inference in large Bayesian semiparametric regression models. In particular, this approach is amenable to handling…

Methodology · Statistics 2016-04-07 M. P. Wand

We show the formal equivalence of linearised self-attention mechanisms and fast weight controllers from the early '90s, where a ``slow" neural net learns by gradient descent to program the ``fast weights" of another net through sequences of…

Machine Learning · Computer Science 2021-06-10 Imanol Schlag , Kazuki Irie , Jürgen Schmidhuber

We provide guarantees for approximate Gaussian Process (GP) regression resulting from two common low-rank kernel approximations: based on random Fourier features, and based on truncating the kernel's Mercer expansion. In particular, we…

Machine Learning · Statistics 2022-02-22 Constantinos Daskalakis , Petros Dellaportas , Aristeidis Panos