Search Results for author:
Found 37 papers, 15 papers with code
Robust Recovery of Subspace Structures by Low-Rank Representation
In this work we address the subspace recovery problem.
Efficient Point-to-Subspace Query in $\ell^1$ with Application to Robust Object Instance Recognition
Motivated by vision tasks such as robust face and object recognition, we consider the following general problem: given a collection of low-dimensional linear subspaces in a high-dimensional ambient (image) space, and a query point (image), efficiently determine the nearest subspace to the query in $\ell^1$ distance.
Finding a sparse vector in a subspace: Linear sparsity using alternating directions
In this paper, we focus on a **planted sparse model** for the subspace: the target sparse vector is embedded in an otherwise random subspace.
Complete Dictionary Recovery over the Sphere
We consider the problem of recovering a complete (i. e., square and invertible) matrix $\mathbf A_0$, from $\mathbf Y \in \mathbb R^{n \times p}$ with $\mathbf Y = \mathbf A_0 \mathbf X_0$, provided $\mathbf X_0$ is sufficiently sparse.
When Are Nonconvex Problems Not Scary?
In this note, we focus on smooth nonconvex optimization problems that obey: (1) all local minimizers are also global; and (2) around any saddle point or local maximizer, the objective has a negative directional curvature.
Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture
We give the first efficient algorithm that provably recovers $\mathbf A_0$ when $\mathbf X_0$ has $O(n)$ nonzeros per column, under suitable probability model for $\mathbf X_0$.
Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method
We consider the problem of recovering a complete (i. e., square and invertible) matrix $\mathbf A_0$, from $\mathbf Y \in \mathbb{R}^{n \times p}$ with $\mathbf Y = \mathbf A_0 \mathbf X_0$, provided $\mathbf X_0$ is sufficiently sparse.
A Geometric Analysis of Phase Retrieval
complex Gaussian) and the number of measurements is large enough ($m \ge C n \log^3 n$), with high probability, a natural least-squares formulation for GPR has the following benign geometric structure: (1) there are no spurious local minimizers, and all global minimizers are equal to the target signal $\mathbf x$, up to a global phase; and (2) the objective function has a negative curvature around each saddle point.
A Local Analysis of Block Coordinate Descent for Gaussian Phase Retrieval
While convergence of the Alternating Direction Method of Multipliers (ADMM) on convex problems is well studied, convergence on nonconvex problems is only partially understood.
A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration
Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as AdaGrad, RMSProp, Adam, AccAdaGrad, \textit{etc}.
Subgradient Descent Learns Orthogonal Dictionaries
This paper concerns dictionary learning, i. e., sparse coding, a fundamental representation learning problem.
Dual-Reference Design for Holographic Coherent Diffraction Imaging
A new reference design is introduced for holographic coherent diffraction imaging.
Inverse Problems, Deep Learning, and Symmetry Breaking
In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output.
Unlocking Inverse Problems Using Deep Learning: Breaking Symmetries in Phase Retrieval
In many physical systems, inputs related by intrinsic system symmetries generate the same output.
Deep Learning Initialized Phase Retrieval
Phase retrieval (PR) consists of estimating 2D or 3D objects from their Fourier magnitudes and takes a central place in scientific imaging.
Towards Low-Photon Nanoscale Imaging: Holographic Phase Retrieval via Maximum Likelihood Optimization
A new algorithmic framework is presented for holographic phase retrieval via maximum likelihood optimization, which allows for practical and robust image reconstruction.
A Prospective Observational Study to Investigate Performance of a Chest X-ray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals
Conclusions and Relevance: AI-based diagnostic tools may serve as an adjunct, but not replacement, for clinical decision support of COVID-19 diagnosis, which largely hinges on exposure history, signs, and symptoms.
Rethinking Transfer Learning for Medical Image Classification
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC).
Phase Retrieval using Single-Instance Deep Generative Prior
Several deep learning methods for phase retrieval exist, but most of them fail on realistic data without precise support information.
Self-Validation: Early Stopping for Single-Instance Deep Generative Priors
Recent works have shown the surprising effectiveness of deep generative models in solving numerous image reconstruction (IR) tasks, even without training data.
NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning
GRANSO is among the first optimization solvers targeting general nonsmooth NCVX problems with nonsmooth constraints, but, as it is implemented in MATLAB and requires the user to provide analytical gradients, GRANSO is often not a convenient choice in machine learning (especially deep learning) applications.
Early Stopping for Deep Image Prior
In this regard, the majority of DIP works for vision tasks only demonstrates the potential of the models -- reporting the peak performance against the ground truth, but provides no clue about how to operationally obtain near-peak performance without access to the groundtruth.
Blind Image Deblurring with Unknown Kernel Size and Substantial Noise
Blind image deblurring (BID) has been extensively studied in computer vision and adjacent fields.
Optimization for Robustness Evaluation beyond $\ell_p$ Metrics
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems.
NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning
Imposing explicit constraints is relatively new but increasingly pressing in deep learning, stimulated by, e. g., trustworthy AI that performs robust optimization over complicated perturbation sets and scientific applications that need to respect physical laws and constraints.
Imbalanced Classification in Medical Imaging via Regrouping
We propose performing imbalanced classification by regrouping majority classes into small classes so that we turn the problem into balanced multiclass classification.
Practical Phase Retrieval Using Double Deep Image Priors
Phase retrieval (PR) concerns the recovery of complex phases from complex magnitudes.
Deep Random Projector: Accelerated Deep Image Prior
Deep image prior (DIP) has shown great promise in tackling a variety of image restoration (IR) and general visual inverse problems, needing no training data.
Interpretable Deep Learning Methods for Multiview Learning
We propose iDeepViewLearn (Interpretable Deep Learning Method for Multiview Learning) for learning nonlinear relationships in data from multiple views while achieving feature selection.
Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspective
However, the economic considerations of the clients, such as fairness and incentive, are yet to be fully explored.
Robust Autoencoders for Collective Corruption Removal
Robust PCA is a standard tool for learning a linear subspace in the presence of sparse corruption or rare outliers.
A Cross-institutional Evaluation on Breast Cancer Phenotyping NLP Algorithms on Electronic Health Records
We developed three types of NLP models (i. e., conditional random field, bi-directional long short-term memory and CancerBERT) to extract cancer phenotypes from clinical texts.
Optimization and Optimizers for Adversarial Robustness
Taking advantage of PWCF and other existing numerical algorithms, we further explore the distinct patterns in the solutions found for solving these optimization problems using various combinations of losses, perturbation models, and optimization algorithms.
Predicting the Future of the CMS Detector: Crystal Radiation Damage and Machine Learning at the LHC
The transparency of each crystal is monitored with a laser monitoring system that tracks changes in the optical properties of the crystals due to radiation from the collision products.
An In-Depth Evaluation of Federated Learning on Biomedical Natural Language Processing
Language models (LMs) such as BERT and GPT have revolutionized natural language processing (NLP).
Federated Learning with Convex Global and Local Constraints
In practice, many machine learning (ML) problems come with constraints, and their applied domains involve distributed sensitive data that cannot be shared with others, e. g., in healthcare.
What is Wrong with End-to-End Learning for Phase Retrieval?
For nonlinear inverse problems that are prevalent in imaging science, symmetries in the forward model are common.
