11 citations · 60 across the 15 of their papers we have counts for
15 papers
Accelerating Diffusion Sampling with Optimized Time Steps
Shuchen Xue, Zhaoqiang Liu, Fei Chen +4
Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typicall…
A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing
Junren Chen, Jonathan Scarlett, Michael K. Ng +1
In generative compressed sensing (GCS), we want to recover a signal from measurements () using a generative prior $\mathbf{x}^*\in G(\ma…
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning
Enze Xie, Lewei Yao, Han Shi +5
Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge…
DDP: Diffusion Model for Dense Visual Prediction
Yuanfeng Ji, Zhe Chen, Enze Xie +6
We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative pa…
Misspecified Phase Retrieval with Generative Priors
Zhaoqiang Liu, Xinshao Wang, Jiulong Liu
In this paper, we study phase retrieval under model misspecification and generative priors. In particular, we aim to estimate an -dimensional signal from i.i.d.…
Projected Gradient Descent Algorithms for Solving Nonlinear Inverse Problems with Generative Priors
Zhaoqiang Liu, Jun Han
In this paper, we propose projected gradient descent (PGD) algorithms for signal estimation from noisy nonlinear measurements. We assume that the unknown -dimensional signal lie…
Non-Iterative Recovery from Nonlinear Observations using Generative Models
Jiulong Liu, Zhaoqiang Liu
In this paper, we aim to estimate the direction of an underlying signal from its nonlinear observations following the semi-parametric single index model (SIM). Unlike conventional…
Generative Principal Component Analysis
Zhaoqiang Liu, Jiulong Liu, Subhroshekhar Ghosh +2
In this paper, we study the problem of principal component analysis with generative modeling assumptions, adopting a general model for the observed matrix that encompasses notable…
Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors
Zhaoqiang Liu, Subhroshekhar Ghosh, Jonathan Scarlett
Compressive phase retrieval is a popular variant of the standard compressive sensing problem in which the measurements only contain magnitude information. In this paper, motivated…
The Generalized Lasso with Nonlinear Observations and Generative Priors
Zhaoqiang Liu, Jonathan Scarlett
In this paper, we study the problem of signal estimation from noisy non-linear measurements when the unknown -dimensional signal is in the range of an -Lipschitz continuous g…
Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors
Zhaoqiang Liu, Selwyn Gomes, Avtansh Tiwari +1
The goal of standard 1-bit compressive sensing is to accurately recover an unknown sparse vector from binary-valued measurements, each indicating the sign of a linear function of t…
Information-Theoretic Lower Bounds for Compressive Sensing with Generative Models
Zhaoqiang Liu, Jonathan Scarlett
It has recently been shown that for compressive sensing, significantly fewer measurements may be required if the sparsity assumption is replaced by the assumption the unknown vecto…
Model Selection for Nonnegative Matrix Factorization by Support Union Recovery
Zhaoqiang Liu
Nonnegative matrix factorization (NMF) has been widely used in machine learning and signal processing because of its non-subtractive, part-based property which enhances interpretab…
The Informativeness of K -Means for Learning Mixture Models
Zhaoqiang Liu, Vincent Y. F. Tan
The learning of mixture models can be viewed as a clustering problem. Indeed, given data samples independently generated from a mixture of distributions, we often would like to fin…
Rank-One NMF-Based Initialization for NMF and Relative Error Bounds under a Geometric Assumption
Zhaoqiang Liu, Vincent Y. F. Tan
We propose a geometric assumption on nonnegative data matrices such that under this assumption, we are able to provide upper bounds (both deterministic and probabilistic) on the re…