no code implementations • 22 Apr 2024 • Safa C. Medin, Gengyan Li, Ruofei Du, Stephan Garbin, Philip Davidson, Gregory W. Wornell, Thabo Beeler, Abhimitra Meka
3D rendering of dynamic face captures is a challenging problem, and it demands improvements on several fronts$\unicode{x2014}$photorealism, efficiency, compatibility, and configurability.
no code implementations • 14 Apr 2024 • Amir Weiss, Yuval Kochman, Gregory W. Wornell
Motivated by the proliferation of mobile devices, we consider a basic form of the ubiquitous problem of time-delay estimation (TDE), but with communication constraints between two non co-located sensors.
no code implementations • 9 Feb 2024 • J. Jon Ryu, Maohao Shen, Soumya Ghosh, Yuheng Bu, Prasanna Sattigeri, Subhro Das, Gregory W. Wornell
This paper explores a modern predictive uncertainty estimation approach, called evidential deep learning (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function.
1 code implementation • 6 Feb 2024 • J. Jon Ryu, Xiangxiang Xu, H. S. Melihcan Erol, Yuheng Bu, Lizhong Zheng, Gregory W. Wornell
Computing eigenvalue decomposition (EVD) of a given linear operator, or finding its leading eigenvalues and eigenfunctions, is a fundamental task in many machine learning and scientific computing problems.
no code implementations • 12 Sep 2023 • Abhin Shah, Devavrat Shah, Gregory W. Wornell
While the traditional maximum likelihood estimator for this class of exponential family is consistent, asymptotically normal, and asymptotically efficient, evaluating it is computationally hard.
1 code implementation • NeurIPS 2023 • Tejas Jayashankar, Gary C. F. Lee, Alejandro Lancho, Amir Weiss, Yury Polyanskiy, Gregory W. Wornell
We propose a new method for separating superimposed sources using diffusion-based generative models.
no code implementations • 8 Jun 2023 • Haobo Chen, Yuheng Bu, Gregory W. Wornell
Double-descent refers to the unexpected drop in test loss of a learning algorithm beyond an interpolating threshold with over-parameterization, which is not predicted by information criteria in their classical forms due to the limitations in the standard asymptotic approach.
no code implementations • 30 May 2023 • Jae Won Choi, Girish Chowdhary, Andrew C. Singer, Hari Vishnu, Amir Weiss, Gregory W. Wornell, Grant Deane
Underwater communication signals typically suffer from distortion due to motion-induced Doppler.
no code implementations • 29 May 2023 • Amir Weiss, Andrew C. Singer, Gregory W. Wornell
Key challenges in developing underwater acoustic localization methods are related to the combined effects of high reverberation in intricate environments.
no code implementations • 14 May 2023 • Amir Weiss, Alejandro Lancho, Yuheng Bu, Gregory W. Wornell
A bilateral (i. e., upper and lower) bound on the mean-square error under a general model mismatch is developed.
1 code implementation • 11 Mar 2023 • Gary C. F. Lee, Amir Weiss, Alejandro Lancho, Yury Polyanskiy, Gregory W. Wornell
We study the single-channel source separation problem involving orthogonal frequency-division multiplexing (OFDM) signals, which are ubiquitous in many modern-day digital communication systems.
no code implementations • 16 Feb 2023 • Abhin Shah, Maohao Shen, Jongha Jon Ryu, Subhro Das, Prasanna Sattigeri, Yuheng Bu, Gregory W. Wornell
To overcome this limitation, we propose a bootstrap-based algorithm that achieves the target level of fairness despite the uncertainty in sensitive attributes.
no code implementations • 14 Nov 2022 • Abhin Shah, Raaz Dwivedi, Devavrat Shah, Gregory W. Wornell
Given an observational study with $n$ independent but heterogeneous units, our goal is to learn the counterfactual distribution for each unit using only one $p$-dimensional sample per unit containing covariates, interventions, and outcomes.
no code implementations • 21 Sep 2022 • Safa C. Medin, Amir Weiss, Frédo Durand, William T. Freeman, Gregory W. Wornell
We transfer what we learn from the synthetic data to the real data using domain adaptation in a completely unsupervised way.
1 code implementation • 11 Sep 2022 • Alejandro Lancho, Amir Weiss, Gary C. F. Lee, Jennifer Tang, Yuheng Bu, Yury Polyanskiy, Gregory W. Wornell
We study the potential of data-driven deep learning methods for separation of two communication signals from an observation of their mixture.
1 code implementation • 22 Aug 2022 • Gary C. F. Lee, Amir Weiss, Alejandro Lancho, Jennifer Tang, Yuheng Bu, Yury Polyanskiy, Gregory W. Wornell
We study the problem of single-channel source separation (SCSS), and focus on cyclostationary signals, which are particularly suitable in a variety of application domains.
no code implementations • 20 Jul 2022 • Amir Weiss, Toros Arikan, Gregory W. Wornell
Direct localization (DLOC) methods, which use the observed data to localize a source at an unknown position in a one-step procedure, generally outperform their indirect two-step counterparts (e. g., using time-difference of arrivals).
no code implementations • Entropy 2022 • Joshua Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory W. Wornell, Leonid Karlinsky and Rogerio Schmidt Feris
As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant.
no code implementations • NeurIPS 2021 • Abhin Shah, Devavrat Shah, Gregory W. Wornell
In this work, we propose a computationally efficient estimator that is consistent as well as asymptotically normal under mild conditions.
1 code implementation • 28 Oct 2021 • Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee, Subhro Das, Rameswar Panda, Prasanna Sattigeri, Gregory W. Wornell
Selective regression allows abstention from prediction if the confidence to make an accurate prediction is not sufficient.
no code implementations • 27 Oct 2021 • Amir Weiss, Toros Arikan, Hari Vishnu, Grant B. Deane, Andrew C. Singer, Gregory W. Wornell
We also derive the Cram\'er-Rao bound for this model, which can be used to guide the placement of collections of receivers so as to optimize localization accuracy.
no code implementations • ICCV 2021 • Prafull Sharma, Miika Aittala, Yoav Y. Schechner, Antonio Torralba, Gregory W. Wornell, William T. Freeman, Fredo Durand
We present a passive non-line-of-sight method that infers the number of people or activity of a person from the observation of a blank wall in an unknown room.
no code implementations • 19 Aug 2021 • Amir Weiss, Everest Huang, Or Ordentlich, Gregory W. Wornell
In a growing number of applications, there is a need to digitize signals whose spectral characteristics are challenging for traditional Analog-to-Digital Converters (ADCs).
no code implementations • 29 Oct 2020 • Amir Weiss, Gregory W. Wornell
One of the main drawbacks of the well-known Direct Position Determination (DPD) method is the requirement that raw signal data be transferred to a common processor.
no code implementations • 28 Oct 2020 • Abhin Shah, Devavrat Shah, Gregory W. Wornell
We consider learning a sparse pairwise Markov Random Field (MRF) with continuous-valued variables from i. i. d samples.
1 code implementation • NeurIPS 2019 • Miika Aittala, Prafull Sharma, Lukas Murmann, Adam B. Yedidia, Gregory W. Wornell, William T. Freeman, Fredo Durand
We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region.
no code implementations • 20 Nov 2019 • Shao-Lun Huang, Anuran Makur, Gregory W. Wornell, Lizhong Zheng
We consider the problem of identifying universal low-dimensional features from high-dimensional data for inference tasks in settings involving learning.
no code implementations • 16 May 2019 • Shao-Lun Huang, Xiangxiang Xu, Lizhong Zheng, Gregory W. Wornell
It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks.
1 code implementation • CVPR 2018 • Manel Baradad, Vickie Ye, Adam B. Yedidia, Frédo Durand, William T. Freeman, Gregory W. Wornell, Antonio Torralba
We present a method for inferring a 4D light field of a hidden scene from 2D shadows cast by a known occluder on a diffuse wall.
no code implementations • ICCV 2017 • Katherine L. Bouman, Vickie Ye, Adam B. Yedidia, Fredo Durand, Gregory W. Wornell, Antonio Torralba, William T. Freeman
We show that walls and other obstructions with edges can be exploited as naturally-occurring "cameras" that reveal the hidden scenes beyond them.