Search Results for author: Zhou Fan

Found 11 papers, 2 papers with code

Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory

no code implementations ICML 2020 Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu

Graph matching, also known as network alignment, aims at recovering the latent vertex correspondence between two unlabeled, edge-correlated weighted graphs.

Graph Matching

Local convexity of the TAP free energy and AMP convergence for Z2-synchronization

no code implementations21 Jun 2021 Michael Celentano, Zhou Fan, Song Mei

This provides a rigorous foundation for variational inference in high dimensions via minimization of the TAP free energy.

Bayesian Inference Variational Inference

Empirical Bayes PCA in high dimensions

1 code implementation21 Dec 2020 Xinyi Zhong, Chang Su, Zhou Fan

When the dimension of data is comparable to or larger than the number of data samples, Principal Components Analysis (PCA) may exhibit problematic high-dimensional noise.

Tree-Projected Gradient Descent for Estimating Gradient-Sparse Parameters on Graphs

no code implementations31 May 2020 Sheng Xu, Zhou Fan, Sahand Negahban

We study estimation of a gradient-sparse parameter vector $\boldsymbol{\theta}^* \in \mathbb{R}^p$, having strong gradient-sparsity $s^*:=\|\nabla_G \boldsymbol{\theta}^*\|_0$ on an underlying graph $G$.

Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks

no code implementations NeurIPS 2020 Zhou Fan, Zhichao Wang

We study the eigenvalue distributions of the Conjugate Kernel and Neural Tangent Kernel associated to multi-layer feedforward neural networks.

Spectral Graph Matching and Regularized Quadratic Relaxations I: The Gaussian Model

no code implementations20 Jul 2019 Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu

Departing from prior spectral approaches that only compare top eigenvectors, or eigenvectors of the same order, GRAMPA first constructs a similarity matrix as a weighted sum of outer products between all pairs of eigenvectors of the two graphs, with weights given by a Cauchy kernel applied to the separation of the corresponding eigenvalues, then outputs a matching by a simple rounding procedure.

Graph Matching

Spectral Graph Matching and Regularized Quadratic Relaxations II: Erdős-Rényi Graphs and Universality

no code implementations20 Jul 2019 Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu

We analyze a new spectral graph matching algorithm, GRAph Matching by Pairwise eigen-Alignments (GRAMPA), for recovering the latent vertex correspondence between two unlabeled, edge-correlated weighted graphs.

Graph Matching

Surfing: Iterative optimization over incrementally trained deep networks

1 code implementation NeurIPS 2019 Ganlin Song, Zhou Fan, John Lafferty

When initialized with random parameters $\theta_0$, we show that the objective $f_{\theta_0}(x)$ is "nice'' and easy to optimize with gradient descent.

Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements

no code implementations15 May 2019 Sheng Xu, Zhou Fan

We consider estimating a piecewise-constant image, or a gradient-sparse signal on a general graph, from noisy linear measurements.

Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space

no code implementations4 Mar 2019 Zhou Fan, Rui Su, Wei-Nan Zhang, Yong Yu

In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-actor networks.

How Well Do Local Algorithms Solve Semidefinite Programs?

no code implementations17 Oct 2016 Zhou Fan, Andrea Montanari

Several probabilistic models from high-dimensional statistics and machine learning reveal an intriguing --and yet poorly understood-- dichotomy.

Cannot find the paper you are looking for? You can Submit a new open access paper.