Search Results for author:
Found 49 papers, 28 papers with code
Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation
For signal recovery from a few measurements, however, un-trained convolutional networks have an intriguing self-regularizing property: Even though the network can perfectly fit any image, the network recovers a natural image from few measurements when trained with gradient descent until convergence.
GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration
The network is a simple shallow network with an efficient block that implements global additive multidimensional averaging operations.
Language models scale reliably with over-training and on downstream tasks
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data
Furthermore, training on diverse data does not compromise in-distribution performance, i. e., a model trained on diverse data yields in-distribution performance at least as good as models trained on the more narrow individual distributions.
A Deep Learning Method for Simultaneous Denoising and Missing Wedge Reconstruction in Cryogenic Electron Tomography
At the same time, DeepDeWedge is simpler than this two-step approach, as it does denoising and missing wedge reconstruction simultaneously rather than sequentially.
K-band: Self-supervised MRI Reconstruction via Stochastic Gradient Descent over K-space Subsets
In each training iteration, rather than using the fully sampled k-space for computing gradients, we use only a small k-space portion.
Approximating Positive Homogeneous Functions with Scale Invariant Neural Networks
Furthermore, we also consider the approximation of general positive homogeneous functions with neural networks.
Implicit Neural Networks with Fourier-Feature Inputs for Free-breathing Cardiac MRI Reconstruction
In this paper, we propose a reconstruction approach based on representing the beating heart with an implicit neural network and fitting the network so that the representation of the heart is consistent with the measurements.
Zero-Shot Noise2Noise: Efficient Image Denoising without any Data
In this work we show that a simple 2-layer network, without any training data or knowledge of the noise distribution, can enable high-quality image denoising at low computational cost.
Monotonic Risk Relationships under Distribution Shifts for Regularized Risk Minimization
Machine learning systems are often applied to data that is drawn from a different distribution than the training distribution.
Test-time Recalibration of Conformal Predictors Under Distribution Shift Based on Unlabeled Examples
To provide such sets, conformal predictors often estimate a cutoff threshold for the probability estimates based on a calibration set.
Scaling Laws For Deep Learning Based Image Reconstruction
Current methods are only trained on a few hundreds or thousands of images as opposed to the millions of examples deep networks are trained on in other domains.
Theoretical Perspectives on Deep Learning Methods in Inverse Problems
In recent years, there have been significant advances in the use of deep learning methods in inverse problems such as denoising, compressive sensing, inpainting, and super-resolution.
Regularization-wise double descent: Why it occurs and how to eliminate it
The risk of overparameterized models, in particular deep neural networks, is often double-descent shaped as a function of the model size.
Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing
We show that for four natural distribution shifts, this method essentially closes the distribution shift performance gap for state-of-the-art architectures for accelerated MRI.
Image-to-Image MLP-mixer for Image Reconstruction
Similar to the original MLP-mixer, the image-to-image MLP-mixer is based exclusively on MLPs operating on linearly-transformed image patches.
Provable Continual Learning via Sketched Jacobian Approximations
We propose a simple approach to overcome this: Regularizing training of a new task with sketches of the Jacobian matrix of past data.
Untrained Graph Neural Networks for Denoising
This paper introduces two untrained graph neural network architectures for graph signal denoising, provides theoretical guarantees for their denoising capabilities in a simple setup, and numerically validates the theoretical results in more general scenarios.
Interpolation can hurt robust generalization even when there is no noise
Numerous recent works show that overparameterization implicitly reduces variance for min-norm interpolators and max-margin classifiers.
Data augmentation for deep learning based accelerated MRI reconstruction with limited data
Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks.
Maximizing the robust margin provably overfits on noiseless data
Numerous recent works show that overparameterization implicitly reduces variance, suggesting vanishing benefits for explicit regularization in high dimensions.
Measuring Robustness in Deep Learning Based Compressive Sensing
In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods.
Data augmentation for deep learning based accelerated MRI reconstruction
Inspired by the success of Data Augmentation (DA) for classification problems, in this paper, we propose a pipeline for data augmentation for image reconstruction tasks arising in medical imaging and explore its effectiveness at reducing the required training data in a variety of settings.
Early Stopping in Deep Networks: Double Descent and How to Eliminate it
Over-parameterized models, such as large deep networks, often exhibit a double descent phenomenon, whereas a function of model size, error first decreases, increases, and decreases at last.
Accelerated MRI with Un-trained Neural Networks
Convolutional Neural Networks (CNNs) are highly effective for image reconstruction problems.
Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation
For signal recovery from a few measurements, however, un-trained convolutional networks have an intriguing self-regularizing property: Even though the network can perfectly fit any image, the network recovers a natural image from few measurements when trained with gradient descent until convergence.
Reducing the Representation Error of GAN Image Priors Using the Deep Decoder
In this paper, we demonstrate a method for reducing the representation error of GAN priors by modeling images as the linear combination of a GAN prior with a Deep Decoder.
Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
A surprising experiment that highlights this architectural bias towards natural images is that one can remove noise and corruptions from a natural image without using any training data, by simply fitting (via gradient descent) a randomly initialized, over-parameterized convolutional generator to the corrupted image.
Image recognition from raw labels collected without annotators
Image classification problems are typically addressed by first collecting examples with candidate labels, second cleaning the candidate labels manually, and third training a deep neural network on the clean examples.
Removing the Representation Error of GAN Image Priors Using the Deep Decoder
In this paper, we demonstrate a method for removing the representation error of a GAN when used as a prior in inverse problems by modeling images as the linear combination of a GAN with a Deep Decoder.
Leveraging inductive bias of neural networks for learning without explicit human annotations
Classification problems today are typically solved by first collecting examples along with candidate labels, second obtaining clean labels from workers, and third training a large, overparameterized deep neural network on the clean examples.
Channel Normalization in Convolutional Neural Network avoids Vanishing Gradients
This effect prevails in deep single-channel linear convolutional networks, and we show that without channel normalization, gradient descent takes at least exponentially many steps to come close to an optimum.
Regularizing linear inverse problems with convolutional neural networks
We demonstrate that with both fixed and parameterized convolutional filters those networks enable representing images with few coefficients.
Deep Denoising: Rate-Optimal Recovery of Structured Signals with a Deep Prior
Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy image.
Adaptive Estimation for Approximate k-Nearest-Neighbor Computations
Algorithms often carry out equally many computations for "easy" and "hard" problem instances.
Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
In this paper, we propose an untrained simple image model, called the deep decoder, which is a deep neural network that can generate natural images from very few weight parameters.
Unsupervised Learning with Stein's Unbiased Risk Estimator
We show that, in the context of image recovery, SURE and its generalizations can be used to train convolutional neural networks (CNNs) for a range of image denoising and recovery problems without any ground truth data.
Rate-Optimal Denoising with Deep Neural Networks
Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy observation.
Approximate Ranking from Pairwise Comparisons
Accordingly, we study the problem of finding approximate rankings from pairwise comparisons.
DiffuserCam: Lensless Single-exposure 3D Imaging
We demonstrate a compact and easy-to-build computational camera for single-shot 3D imaging.
The Sample Complexity of Online One-Class Collaborative Filtering
We consider the online one-class collaborative filtering (CF) problem that consists of recommending items to users over time in an online fashion based on positive ratings only.
Active Ranking from Pairwise Comparisons and when Parametric Assumptions Don't Help
We first analyze a sequential ranking algorithm that counts the number of comparisons won, and uses these counts to decide whether to stop, or to compare another pair of items, chosen based on confidence intervals specified by the data collected up to that point.
Scalable and interpretable product recommendations via overlapping co-clustering
We consider the problem of generating interpretable recommendations by identifying overlapping co-clusters of clients and products, based only on positive or implicit feedback.
Dimensionality-reduced subspace clustering
Subspace clustering refers to the problem of clustering unlabeled high-dimensional data points into a union of low-dimensional linear subspaces, whose number, orientations, and dimensions are all unknown.
Subspace clustering of dimensionality-reduced data
Subspace clustering refers to the problem of clustering unlabeled high-dimensional data points into a union of low-dimensional linear subspaces, assumed unknown.
Neighborhood Selection for Thresholding-based Subspace Clustering
Subspace clustering refers to the problem of clustering high-dimensional data points into a union of low-dimensional linear subspaces, where the number of subspaces, their dimensions and orientations are all unknown.
Compressive Nonparametric Graphical Model Selection For Time Series
We propose a method for inferring the conditional indepen- dence graph (CIG) of a high-dimensional discrete-time Gaus- sian vector random process from finite-length observations.
Robust Subspace Clustering via Thresholding
We propose a simple low-complexity subspace clustering algorithm, which applies spectral clustering to an adjacency matrix obtained by thresholding the correlations between data points.
Noisy Subspace Clustering via Thresholding
We consider the problem of clustering noisy high-dimensional data points into a union of low-dimensional subspaces and a set of outliers.
