no code implementations • 12 Sep 2023 • Shaik Basheeruddin Shah, Pradyumna Pradhan, Wei Pu, Ramunaidu Randhi, Miguel R. D. Rodrigues, Yonina C. Eldar
Hence, we provide conditions, in terms of the network width and the number of training samples, on these unfolded networks for the PL$^*$ condition to hold.
no code implementations • 19 Apr 2023 • Avner Shultzman, Eyar Azar, Miguel R. D. Rodrigues, Yonina C. Eldar
In practice, model-based neural networks exhibit higher generalization capability compared to ReLU neural networks.
no code implementations • 2 Oct 2022 • Gholamali Aminian, Saeed Masiha, Laura Toni, Miguel R. D. Rodrigues
In this work, we suggest a creative method, i. e., the Auxiliary Distribution Method, that derives new upper bounds on generalization errors that are appropriate for supervised learning scenarios.
no code implementations • 15 Sep 2022 • Gholamali Aminian, Armin Behnamnia, Roberto Vega, Laura Toni, Chengchun Shi, Hamid R. Rabiee, Omar Rivasplata, Miguel R. D. Rodrigues
We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data.
no code implementations • 29 Jun 2022 • Jonathan Scarlett, Reinhard Heckel, Miguel R. D. Rodrigues, Paul Hand, Yonina C. Eldar
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.
no code implementations • 24 Feb 2022 • Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili, Laura Toni, Miguel R. D. Rodrigues
A common assumption in semi-supervised learning is that the labeled, unlabeled, and test data are drawn from the same distribution.
no code implementations • 20 Oct 2021 • Wei Pu, Chao Zhou, Yonina C. Eldar, Miguel R. D. Rodrigues
In this paper, we consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications.
no code implementations • 28 Jul 2021 • Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel R. D. Rodrigues, Gregory Wornell
As a result, they may fail to characterize the exact generalization ability of a learning algorithm.
no code implementations • 3 Feb 2021 • Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues
Generalization error bounds are critical to understanding the performance of machine learning models.
no code implementations • 1 Jan 2021 • Natalia Martinez, Martin Bertran, Afroditi Papadaki, Miguel R. D. Rodrigues, Guillermo Sapiro
With the wide adoption of machine learning algorithms across various application domains, there is a growing interest in the fairness properties of such algorithms.
no code implementations • 23 Oct 2020 • Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues
Generalization error bounds are critical to understanding the performance of machine learning models.
no code implementations • 16 Sep 2020 • Wei Pu, Barak Sober, Nathan Daly, Zahra Sabetsarvestani, Catherine Higgitt, Ingrid Daubechies, Miguel R. D. Rodrigues
These features are then used to (1) reproduce both of the original RGB images, (2) reconstruct the hypothetical separated X-ray images, and (3) regenerate the mixed X-ray image.
no code implementations • 18 Jun 2020 • Jaweria Amjad, Zhaoyan Lyu, Miguel R. D. Rodrigues
There are various inverse problems -- including reconstruction problems arising in medical imaging -- where one is often aware of the forward operator that maps variables of interest to the observations.
no code implementations • 2 Apr 2019 • Daniel Jakubovitz, Miguel R. D. Rodrigues, Raja Giryes
We focus on the task of semi-supervised transfer learning, in which unlabeled samples from the target dataset are available during the network training on the source dataset.
no code implementations • 31 Jan 2019 • Jaweria Amjad, Zhaoyan Lyu, Miguel R. D. Rodrigues
Inverse problems arise in a number of domains such as medical imaging, remote sensing, and many more, relying on the use of advanced signal and image processing approaches -- such as sparsity-driven techniques -- to determine their solution.
no code implementations • 3 Aug 2018 • Daniel Jakubovitz, Raja Giryes, Miguel R. D. Rodrigues
Deep learning models have lately shown great performance in various fields such as computer vision, speech recognition, speech translation, and natural language processing.
1 code implementation • 26 Jun 2018 • Pingfan Song, Lior Weizman, Joao F. C. Mota, Yonina C. Eldar, Miguel R. D. Rodrigues
In this paper, we propose a Coupled Dictionary Learning based multi-contrast MRI reconstruction (CDLMRI) approach to leverage an available guidance contrast to restore the target contrast.
no code implementations • 26 Jun 2018 • Pingfan Song, Miguel R. D. Rodrigues
The first stage performs joint sparse transform for multimodal images with respect to a group of learned coupled dictionaries, followed by a shrinkage operation on the sparse representations.
no code implementations • 26 Jun 2018 • Pingfan Song, Miguel R. D. Rodrigues
In real-world scenarios, many data processing problems often involve heterogeneous images associated with different imaging modalities.
1 code implementation • 25 Sep 2017 • Pingfan Song, Xin Deng, João F. C. Mota, Nikos Deligiannis, Pier Luigi Dragotti, Miguel R. D. Rodrigues
This paper proposes a new approach to construct a high-resolution (HR) version of a low-resolution (LR) image given another HR image modality as reference, based on joint sparse representations induced by coupled dictionaries.
no code implementations • 23 May 2017 • Jure Sokolic, Qiang Qiu, Miguel R. D. Rodrigues, Guillermo Sapiro
Confronted with this challenge, in this paper we open a new line of research, where the security, privacy, and fairness is learned and used in a closed environment.
no code implementations • 14 Oct 2016 • Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel R. D. Rodrigues
We show that whereas the generalization error of a non-invariant classifier is proportional to the complexity of the input space, the generalization error of an invariant classifier is proportional to the complexity of the base space.
no code implementations • 14 Jul 2016 • Nikos Deligiannis, Joao F. C. Mota, Bruno Cornelis, Miguel R. D. Rodrigues, Ingrid Daubechies
Our dictionary learning framework can be tailored both to a single- and a multi-scale framework, with the latter leading to a significant performance improvement.
no code implementations • 11 Jul 2016 • Hugo Reboredo, Francesco Renna, Robert Calderbank, Miguel R. D. Rodrigues
This paper studies the classification of high-dimensional Gaussian signals from low-dimensional noisy, linear measurements.
no code implementations • 26 May 2016 • Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel R. D. Rodrigues
The generalization error of deep neural networks via their classification margin is studied in this work.
no code implementations • 20 May 2016 • Nikos Deligiannis, João F. C. Mota, Bruno Cornelis, Miguel R. D. Rodrigues, Ingrid Daubechies
In support of art investigation, we propose a new source sepa- ration method that unmixes a single X-ray scan acquired from double-sided paintings.
no code implementations • 7 Aug 2015 • Jure Sokolic, Francesco Renna, Robert Calderbank, Miguel R. D. Rodrigues
This paper considers the classification of linear subspaces with mismatched classifiers.
2 code implementations • 11 Mar 2015 • Joao F. C. Mota, Nikos Deligiannis, Aswin C. Sankaranarayanan, Volkan Cevher, Miguel R. D. Rodrigues
We propose and analyze an online algorithm for reconstructing a sequence of signals from a limited number of linear measurements.
no code implementations • 1 Dec 2014 • Francesco Renna, Liming Wang, Xin Yuan, Jianbo Yang, Galen Reeves, Robert Calderbank, Lawrence Carin, Miguel R. D. Rodrigues
These conditions, which are reminiscent of the well-known Slepian-Wolf and Wyner-Ziv conditions, are a function of the number of linear features extracted from the signal of interest, the number of linear features extracted from the side information signal, and the geometry of these signals and their interplay.
1 code implementation • 10 Oct 2014 • João F. C. Mota, Nikos Deligiannis, Miguel R. D. Rodrigues
We address the problem of Compressed Sensing (CS) with side information.
2 code implementations • 22 Aug 2014 • Joao F. C. Mota, Nikos Deligiannis, Miguel R. D. Rodrigues
Our bounds and geometrical interpretations reveal that if the prior information has good enough quality, L1-L1 minimization improves the performance of CS dramatically.
Information Theory Information Theory