paper-with-me

Papers

Orthogonal Random Features: Explicit Forms and Sharp Inequalities

2023-10-11 · Nizar Demni, Hachem Kadri

Random features have been introduced to scale up kernel methods via randomization techniques. In particular, random Fourier features and orthogonal random features were used to approximate the popular Gaussian kernel. Random Fourier features are built in this case using a random Gaussian matrix. In this work, we analyze the bias and the variance of the kernel approximation based on orthogonal random features which makes use of Haar orthogonal matrices. We provide explicit expressions for these quantities using normalized Bessel functions, showing that orthogonal random features does not approximate the Gaussian kernel but a Bessel kernel. We also derive sharp exponential bounds supporting the view that orthogonal random features are less dispersed than random Fourier features.

📄 PDF Abstract BibTeX arXiv:2310.07370

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks

2026-02-11 · Constantin Kogler, Tassilo Schwarz, Samuel Kittle arxiv

Effective initialization in deep networks requires an understanding of random neural networks. In this work, a rigorous probabilistic analysis of deep bias-free random Leaky ReLU networks is provided. We prove a Law of L…

Spatial Orthogonal Refinement for Robust RGB-Event Visual Object Tracking

2026-03-29 · Dexing Huang, Shiao Wang, Fan Zhang, Xiao Wang arxiv

Robust visual object tracking (VOT) remains challenging in high-speed motion scenarios, where conventional RGB sensors suffer from severe motion blur and performance degradation. Event cameras, with microsecond temporal …

Visual Object Tracking

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning

2023-08-06 · Nikhil Ghosh, Spencer Frei, Wooseok Ha, Bin Yu

In this work, we investigate the dynamics of stochastic gradient descent (SGD) when training a single-neuron autoencoder with linear or ReLU activation on orthogonal data. We show that for this non-convex problem, random…

feature selection

Orthogonal Random Features

2016-10-28 · NeurIPS 2016 12 · Felix X. Yu, Ananda Theertha Suresh, Krzysztof Choromanski, Daniel Holtmann-Rice 외

We present an intriguing discovery related to Random Fourier Features: in Gaussian kernel approximation, replacing the random Gaussian matrix by a properly scaled random orthogonal matrix significantly decreases kernel a…

Random Orthogonalization for Federated Learning in Massive MIMO Systems

2022-10-18 · Xizixiang Wei, Cong Shen, Jing Yang, H. Vincent Poor

We propose a novel communication design, termed random orthogonalization, for federated learning (FL) in a massive multiple-input and multiple-output (MIMO) wireless system. The key novelty of random orthogonalization co…

Federated Learning