Search Results for author:
Found 27 papers, 10 papers with code
Practical Phase Retrieval Using Double Deep Image Priors
Phase retrieval (PR) concerns the recovery of complex phases from complex magnitudes.
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.
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.
Optimization for Robustness Evaluation beyond $\ell_p$ Metrics
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems.
Blind Image Deblurring with Unknown Kernel Size and Substantial Noise
Blind image deblurring (BID) has been extensively studied in computer vision and adjacent fields.
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.
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.
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.
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.
Rethinking Transfer Learning for Medical Image Classification
For example, on the BIMCV COVID-19 classification dataset, we obtain improved performance with around $1/4$ model size and $2/3$ inference time compared to the standard full TL model.
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.
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.
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.
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.
Inverse Problems, Deep Learning, and Symmetry Breaking
In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output.
Dual-Reference Design for Holographic Coherent Diffraction Imaging
A new reference design is introduced for holographic coherent diffraction imaging.
Subgradient Descent Learns Orthogonal Dictionaries
This paper concerns dictionary learning, i. e., sparse coding, a fundamental representation learning problem.
Weighted AdaGrad with Unified Momentum
Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as Nadam, AccAdaGrad, \textit{etc}.
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 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.
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.
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 $\mathbf X_0$.
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
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.
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.
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.
Robust Recovery of Subspace Structures by Low-Rank Representation
In this work we address the subspace recovery problem.
