35 accepted papers
Diffusion models deliver state-of-the-art generative performance across diverse modalities but remain computationally expensive due to their inherently iterative sampling process. Existing training-free acceleration methods typically improve numerical solvers for the reverse-time ODE, yet their effe
The distortion–perception (D–P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between distortion performance and perceptual quality. Enabling flexible traversal of the D-P tradeoff at inference time is crucial for practical applications. …
Classifier-Free Guidance (CFG) is widely used to improve conditional fidelity in diffusion models, but its impact on sampling dynamics remains poorly understood. Prior studies, often restricted to unimodal conditional distributions or simplified cases, provide only a partial picture. We analyze CFG…
Classifier-free guidance (CFG) has emerged as a pivotal advancement in text-to-image latent diffusion models, establishing itself as a cornerstone technique for achieving high-quality image synthesis. However, under high guidance weights, where text-image alignment is significantly enhanced, CFG als…
Diffusion-based inverse algorithms have shown remarkable performance across various inverse problems, yet their reliance on numerous denoising steps incurs high computational costs. While recent developments of fast diffusion ODE solvers offer effective acceleration for diffusion sampling without o…
Time Series Anomaly Detection (TSAD) methods often require large datasets and extensive domain knowledge, limiting their effectiveness in data-scarce environments. We introduce a novel unsupervised TSAD approach based on path signatures, which efficiently extracts shape features from time series dat…
Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks. Existing works have leveraged the fact that In-distribution (ID) samples form a subspace in the feature space, achieving state-of-the-art (SOTA) performance. However, the comprehensive characteristi…
The recent emergence of diffusion models has significantly advanced the precision of learnable priors, presenting innovative avenues for addressing inverse problems. Previous works have endeavored to integrate diffusion priors into the maximum a posteriori estimation (MAP) framework and design optim…
Traditional Time-series Anomaly Detection (TAD) methods often struggle with the composite nature of complex time-series data and a diverse array of anomalies. We introduce TADNet, an end-to-end TAD model that leverages Seasonal-Trend Decomposition to link various types of anomalies to specific decom…
Benign overfitting refers to a recently discovered intriguing phenomenon that over-parameterized neural networks, in many cases, can fit the training data perfectly but still generalize well, surprisingly contrary to the traditional belief that overfitting is harmful for generalization. In spite of…
We consider the problem of distributed principal component analysis (PCA) where the data samples are dispersed across different agents. Despite the rich literature on this problem under various specific settings, there is still a lack of efficient algorithms that are amenable to decentralized and as…
We study the problem of reconstructing a continuous multidimensional signal from a small number of samples under Fourier constraints assuming that the Fourier power spectrum of the signal has some desirable properties, e.g. being compactly supported, being sparse. We further assume that the Fourier…
Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and horizon length $H$, substantial progress has been achieved toward…
Low-complexity models such as linear function representation play a pivotal role in enabling sample-efficient reinforcement learning (RL). The current paper pertains to a scenario with value-based linear representation, which postulates linear realizability of the optimal Q-function (also called the…
Spectral method is a commonly used scheme to cluster data points lying close to Union of Subspaces, a task known as Subspace Clustering. The typical usage is to construct a Random Geometry Graph first and then apply spectral method to the graph to obtain clustering result. The latter step has been c…
Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. Focusing on the synchronous setting (such that independent samples for all state-action pairs are queried via a generative model in each it…
Subspace clustering has attracted much attention due to its successful application on many data mining and computer vision tasks. However, most subspace clustering algorithms suffer from the scalability and the curse of dimensionality problems. When the volume or the dimension of the datasets become…
We investigate the sample efficiency of reinforcement learning in a $\gamma$-discounted infinite-horizon Markov decision process (MDP) with state space S and action space A, assuming access to a generative model. Despite a number of prior work tackling this problem, a complete picture of the trade-…
In this work, a distributed non-orthogonal pilot design approach is proposed to tackle the pilot contamination problem in multi-cell massive multiple input multiple output (MIMO) systems. The pilot signals are designed under power constraints by minimizing the total mean square errors (MSEs) of the…
Detecting subspace signals is an important problem in radar and sonar signal processing, hyperspectral image processing, wireless communication, and other fields. Among these problems, a typical scenario is that one needs to detect a signal lying in a given target subspace, contaminated by interfere…
Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP), based on a single trajectory of Markovian samples induced by a behavior policy. Focusing on a $\gamma$-discounted MDP with state space S and action space A, we demonstrate tha…
Hyperspectral images (HSIs) clustering problem is a challenge and valuable task due to its inherent complexity and abundant spectral information. Sparse subspace clustering (SSC) and SSC-based methods are widely used in this problem and demonstrate excellent performance. However, considering that HS…
Labelled data are often required to train an acoustic scene classification system. However, it is time-consuming and expensive to label the data manually. An unsupervised clustering algorithm can be used to facilitate the labelling process by dividing the acoustic data into different categories. Nev…
Compressed sensing seeks to recover an unknown sparse vector from undersampled rate measurements. Since its introduction, there have been enormous works on compressed sensing that develop efficient algorithms for sparse signal recovery. The restricted isometry property (RIP) has become the dominant…
Sampling and reconstruction is a fundamentally important problem in the field of graph signal processing. Many works have been contributed to reconstructing bandlimited signals from measurements taken on a known subset of vertices. However, in some cases, the vertex defects occur randomly over the g…
In a change-point detection problem, a sequence of signals switches from one distribution to another at an unknown time step, and the goal is to quickly and reliably detect this change. By providing new insight into signal processing and data analysis, graph signal processing promises various applic…
Phase retrieval has been an attractive problem, and many algorithms have been proposed. Randomized Kaczmarz method is a fast iterative method with good performance in both convergence rate and computational cost with theoretical analysis. However, they all assume that the iteratively updated variabl…
In this work we propose to fit a sparse logistic regression model by a weakly convex regularized nonconvex optimization problem. The idea is based on the finding that a weakly convex function as an approximation of the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.…
Dimension reduction plays an essential role when decreasing the complexity of solving large-scale problems. The well-known Johnson-Lindenstrauss (JL) Lemma and Restricted Isometry Property (RIP) admit the use of random projection to reduce the dimension while keeping the Euclidean distance, which le…
Discovering the underlying structure of a high-dimensional signal or big data has always been a challenging topic, and has become harder to tackle especially when the observations are exposed to arbitrary sparse perturbations. In this paper, built on the model of a union of subspaces (UoS) with spar…
Stochastic optimization finds wide application in signal processing, online learning, and network problems, especially problems processing large-scale data. We propose an Incremental Constraint Averaging Projection Method (ICAPM) that is tailored to optimization problems involving a large number of…
Sparse subspace clustering (SSC) is a technique to partition unlabeled samples according to the subspaces they locate in. With the rapid increase of data amount, efficiently downsampling a big dataset, while at the same time keeping the structure of subspaces, becomes an important topic for SSC. In…
Sparse signal recovery in the static case has been well studied under the framework of Compressive Sensing (CS), while in recent years more attention has also been paid to the dynamic case. In this paper, enlightened by the idea of modified-CS with partially known support, and based on a non-convex…
In solving the problem of sparse recovery, non-convex techniques have been paid much more attention than ever before, among which the most widely used one is ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> minimization with p ∈ (0, 1). It has…
In this paper, we work on the problem of subspace estimation from random downsamplings of its projection matrix. An optimization problem on the Grassmann manifold is formulated for projection matrix completion, and an iterative gradient descend line-search algorithm on the Grassmann manifold (GGDLS)…