Search Results for author: Jeremias Sulam

Found 28 papers, 15 papers with code

What's in a Prior? Learned Proximal Networks for Inverse Problems

1 code implementation22 Oct 2023 Zhenghan Fang, Sam Buchanan, Jeremias Sulam

Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed.

Sparsity-aware generalization theory for deep neural networks

no code implementations1 Jul 2023 Ramchandran Muthukumar, Jeremias Sulam

In this paper, we present a new approach to analyzing generalization for deep feed-forward ReLU networks that takes advantage of the degree of sparsity that is achieved in the hidden layer activations.

Understanding Noise-Augmented Training for Randomized Smoothing

1 code implementation8 May 2023 Ambar Pal, Jeremias Sulam

This method relies on taking a majority vote of any base classifier over multiple noise-perturbed inputs to obtain a smoothed classifier, and it remains the tool of choice to certify deep and complex neural network models.

Binary Classification

How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Control

1 code implementation7 Feb 2023 Jacopo Teneggi, Matthew Tivnan, J. Webster Stayman, Jeremias Sulam

Score-based generative modeling, informally referred to as diffusion models, continue to grow in popularity across several important domains and tasks.

Computed Tomography (CT) Conformal Prediction +1

Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT

1 code implementation29 Nov 2022 Jacopo Teneggi, Paul H. Yi, Jeremias Sulam

We find that strong supervision (i. e., learning with local image-level annotations) and weak supervision (i. e., learning with only global examination-level labels) achieve comparable performance in examination-level hemorrhage detection (the task of selecting the images in an examination that show signs of hemorrhage) as well as in image-level hemorrhage detection (highlighting those signs within the selected images).

Computed Tomography (CT) Multiple Instance Learning +1

DeepSTI: Towards Tensor Reconstruction using Fewer Orientations in Susceptibility Tensor Imaging

no code implementations9 Sep 2022 Zhenghan Fang, Kuo-Wei Lai, Peter van Zijl, Xu Li, Jeremias Sulam

Experimental results using both simulation and in vivo human data demonstrate great improvement over state-of-the-art algorithms in terms of the reconstructed tensor image, principal eigenvector maps and tractography results, while allowing for tensor reconstruction with MR phase measured at much less than six different orientations.

Image Reconstruction

SHAP-XRT: The Shapley Value Meets Conditional Independence Testing

1 code implementation14 Jul 2022 Jacopo Teneggi, Beepul Bharti, Yaniv Romano, Jeremias Sulam

As a result, we further our understanding of Shapley-based explanation methods from a novel perspective and characterize the conditions under which one can make statistically valid claims about feature importance via the Shapley value.

Binary Classification Decision Making +3

Adversarial robustness of sparse local Lipschitz predictors

no code implementations26 Feb 2022 Ramchandran Muthukumar, Jeremias Sulam

This work studies the adversarial robustness of parametric functions composed of a linear predictor and a non-linear representation map.

Adversarial Robustness

Entrywise Recovery Guarantees for Sparse PCA via Sparsistent Algorithms

no code implementations8 Feb 2022 Joshua Agterberg, Jeremias Sulam

Sparse Principal Component Analysis (PCA) is a prevalent tool across a plethora of subfields of applied statistics.

Deciphering antibody affinity maturation with language models and weakly supervised learning

no code implementations14 Dec 2021 Jeffrey A. Ruffolo, Jeffrey J. Gray, Jeremias Sulam

Understanding the composition of an individual's immune repertoire can provide insights into this process and reveal potential therapeutic antibodies.

Language Modelling Multiple Instance Learning +1

Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images

1 code implementation22 Sep 2021 Zhenzhen Wang, Carla Saoud, Sintawat Wangsiricharoen, Aaron W. James, Aleksander S. Popel, Jeremias Sulam

Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development.

Deep Attention Multiple Instance Learning +1

A Geometric Analysis of Neural Collapse with Unconstrained Features

1 code implementation NeurIPS 2021 Zhihui Zhu, Tianyu Ding, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu

In contrast to existing landscape analysis for deep neural networks which is often disconnected from practice, our analysis of the simplified model not only does it explain what kind of features are learned in the last layer, but it also shows why they can be efficiently optimized in the simplified settings, matching the empirical observations in practical deep network architectures.

Fast Hierarchical Games for Image Explanations

1 code implementation13 Apr 2021 Jacopo Teneggi, Alexandre Luster, Jeremias Sulam

As modern complex neural networks keep breaking records and solving harder problems, their predictions also become less and less intelligible.

Image Classification Multiple Instance Learning

Learning to solve TV regularised problems with unrolled algorithms

1 code implementation NeurIPS 2020 Hamza Cherkaoui, Jeremias Sulam, Thomas Moreau

In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems.

Learning to solve TV regularized problems with unrolled algorithms

no code implementations19 Oct 2020 Hamza Cherkaoui, Jeremias Sulam, Thomas Moreau

In this paper, we accelerate such iterative algorithms by unfolding proximal gradient descent solvers in order to learn their parameters for 1D TV regularized problems.

Learned Proximal Networks for Quantitative Susceptibility Mapping

1 code implementation11 Aug 2020 Kuo-Wei Lai, Manisha Aggarwal, Peter van Zijl, Xu Li, Jeremias Sulam

More importantly, this framework is believed to be the first deep learning QSM approach that can naturally handle an arbitrary number of phase input measurements without the need for any ad-hoc rotation or re-training.

Image Reconstruction

Deep Learning in Protein Structural Modeling and Design

no code implementations16 Jul 2020 Wenhao Gao, Sai Pooja Mahajan, Jeremias Sulam, Jeffrey J. Gray

Deep learning is catalyzing a scientific revolution fueled by big data, accessible toolkits, and powerful computational resources, impacting many fields including protein structural modeling.

Recovery and Generalization in Over-Realized Dictionary Learning

no code implementations11 Jun 2020 Jeremias Sulam, Chong You, Zhihui Zhu

We thoroughly demonstrate this observation in practice and provide an analysis of this phenomenon by tying recovery measures to generalization bounds.

Dictionary Learning Generalization Bounds

Conformal Symplectic and Relativistic Optimization

1 code implementation NeurIPS 2020 Guilherme França, Jeremias Sulam, Daniel P. Robinson, René Vidal

Arguably, the two most popular accelerated or momentum-based optimization methods in machine learning are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order differential equation with friction.

Friction

A Local Block Coordinate Descent Algorithm for the Convolutional Sparse Coding Model

2 code implementations1 Nov 2018 Ev Zisselman, Jeremias Sulam, Michael Elad

The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities.

Image Inpainting

MMSE Approximation For Sparse Coding Algorithms Using Stochastic Resonance

no code implementations26 Jun 2018 Dror Simon, Jeremias Sulam, Yaniv Romano, Yue M. Lu, Michael Elad

The proposed method adds controlled noise to the input and estimates a sparse representation from the perturbed signal.

On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks

2 code implementations2 Jun 2018 Jeremias Sulam, Aviad Aberdam, Amir Beck, Michael Elad

Parsimonious representations are ubiquitous in modeling and processing information.

Adversarial Noise Attacks of Deep Learning Architectures -- Stability Analysis via Sparse Modeled Signals

no code implementations29 May 2018 Yaniv Romano, Aviad Aberdam, Jeremias Sulam, Michael Elad

Despite their impressive performance, deep convolutional neural networks (CNNs) have been shown to be sensitive to small adversarial perturbations.

General Classification

Multi-Layer Sparse Coding: The Holistic Way

no code implementations25 Apr 2018 Aviad Aberdam, Jeremias Sulam, Michael Elad

The recently proposed multi-layer sparse model has raised insightful connections between sparse representations and convolutional neural networks (CNN).

Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning

no code implementations29 Aug 2017 Jeremias Sulam, Vardan Papyan, Yaniv Romano, Michael Elad

We show that the training of the filters is essential to allow for non-trivial signals in the model, and we derive an online algorithm to learn the dictionaries from real data, effectively resulting in cascaded sparse convolutional layers.

Dictionary Learning

Convolutional Dictionary Learning via Local Processing

1 code implementation ICCV 2017 Vardan Papyan, Yaniv Romano, Jeremias Sulam, Michael Elad

Convolutional Sparse Coding (CSC) is an increasingly popular model in the signal and image processing communities, tackling some of the limitations of traditional patch-based sparse representations.

Dictionary Learning Image Inpainting +1

Trainlets: Dictionary Learning in High Dimensions

no code implementations31 Jan 2016 Jeremias Sulam, Boaz Ophir, Michael Zibulevsky, Michael Elad

Sparse representations has shown to be a very powerful model for real world signals, and has enabled the development of applications with notable performance.

Dictionary Learning Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.