Alexandros G. Dimakis

research

∙ 07/02/2023

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

We present the first framework to solve linear inverse problems leveragi...

0 Litu Rout, et al. ∙

research

∙ 06/06/2023

One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solvers

A key problem when modeling signal integrity for passive filters and int...

0 Sriram Ravula, et al. ∙

research

∙ 06/05/2023

Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models

Diffusion-based generative models have been used as powerful priors for ...

0 Sriram Ravula, et al. ∙

research

∙ 05/30/2023

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

We present the first diffusion-based framework that can learn an unknown...

0 Giannis Daras, et al. ∙

research

∙ 03/06/2023

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers

We develop a framework for non-asymptotic analysis of deterministic samp...

0 Sitan Chen, et al. ∙

research

∙ 02/17/2023

Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent

Imperfect score-matching leads to a shift between the training and the s...

0 Giannis Daras, et al. ∙

research

∙ 11/30/2022

Multiresolution Textual Inversion

We extend Textual Inversion to learn pseudo-words that represent a conce...

0 Giannis Daras, et al. ∙

research

∙ 10/20/2022

Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve

We find a surprising connection between multitask learning and robustnes...

1 Giannis Daras, et al. ∙

research

∙ 10/14/2022

Zonotope Domains for Lagrangian Neural Network Verification

Neural network verification aims to provide provable bounds for the outp...

0 Matt Jordan, et al. ∙

research

∙ 09/12/2022

Soft Diffusion: Score Matching for General Corruptions

We define a broader family of corruption processes that generalizes prev...

6 Giannis Daras, et al. ∙

research

∙ 06/18/2022

Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

We prove fast mixing and characterize the stationary distribution of the...

7 Giannis Daras, et al. ∙

research

∙ 06/01/2022

Discovering the Hidden Vocabulary of DALLE-2

We discover that DALLE-2 seems to have a hidden vocabulary that can be u...

11 Giannis Daras, et al. ∙

research

∙ 12/05/2021

Deblurring via Stochastic Refinement

Image deblurring is an ill-posed problem with multiple plausible solutio...

0 Jay Whang, et al. ∙

research

∙ 10/14/2021

Inverse Problems Leveraging Pre-trained Contrastive Representations

We study a new family of inverse problems for recovering representations...

0 Sriram Ravula, et al. ∙

research

∙ 08/03/2021

Robust Compressed Sensing MRI with Deep Generative Priors

The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep gen...

15 Ajil Jalal, et al. ∙

research

∙ 07/06/2021

Provable Lipschitz Certification for Generative Models

We present a scalable technique for upper bounding the Lipschitz constan...

0 Matt Jordan, et al. ∙

research

∙ 06/23/2021

Fairness for Image Generation with Uncertain Sensitive Attributes

This work tackles the issue of fairness in the context of generative pro...

0 Ajil Jalal, et al. ∙

research

∙ 06/21/2021

Instance-Optimal Compressed Sensing via Posterior Sampling

We characterize the measurement complexity of compressed sensing of sign...

6 Ajil Jalal, et al. ∙

research

∙ 06/05/2021

Neural Distributed Source Coding

Distributed source coding is the task of encoding an input in the absenc...

0 Jay Whang, et al. ∙

research

∙ 02/15/2021

Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

We propose Intermediate Layer Optimization (ILO), a novel optimization a...

13 Giannis Daras, et al. ∙

research

∙ 12/15/2020

Model-Based Deep Learning

Signal processing, communications, and control have traditionally relied...

86 Nir Shlezinger, et al. ∙

research

∙ 10/11/2020

SMYRF: Efficient Attention using Asymmetric Clustering

We propose a novel type of balanced clustering algorithm to approximate ...

34 Giannis Daras, et al. ∙

research

∙ 06/16/2020

Robust compressed sensing of generative models

The goal of compressed sensing is to estimate a high dimensional vector ...

4 Ajil Jalal, et al. ∙

research

∙ 05/12/2020

Deep Learning Techniques for Inverse Problems in Imaging

Recent work in machine learning shows that deep neural networks can be u...

11 Gregory Ongie, et al. ∙

research

∙ 03/18/2020

Compressed Sensing with Invertible Generative Models and Dependent Noise

We study image inverse problems with invertible generative priors, speci...

11 Jay Whang, et al. ∙

research

∙ 03/02/2020

Exactly Computing the Local Lipschitz Constant of ReLU Networks

The Lipschitz constant of a neural network is a useful metric for provab...

24 Matt Jordan, et al. ∙

research

∙ 02/26/2020

Conditional Sampling from Invertible Generative Models with Applications to Inverse Problems

We consider uncertainty aware compressive sensing when the prior distrib...

10 Erik M. Lindgren, et al. ∙

research

∙ 11/27/2019

Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models

We introduce a new local sparse attention layer that preserves two-dimen...

41 Giannis Daras, et al. ∙

research

∙ 10/17/2019

Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls

Large-scale machine learning training suffers from two prior challenges,...

17 Jiacheng Zhuo, et al. ∙

research

∙ 10/15/2019

SGD Learns One-Layer Networks in WGANs

Generative adversarial networks (GANs) are a widely used framework for l...

44 Qi Lei, et al. ∙

research

∙ 09/04/2019

Learning Distributions Generated by One-Layer ReLU Networks

We consider the problem of estimating the parameters of a d-dimensional ...

22 Shanshan Wu, et al. ∙

research

∙ 06/18/2019

Inverting Deep Generative models, One layer at a time

We study the problem of inverting a deep generative model with ReLU acti...

23 Qi Lei, et al. ∙

research

∙ 06/06/2019

Primal-Dual Block Frank-Wolfe

We propose a variant of the Frank-Wolfe algorithm for solving a class of...

1 Qi Lei, et al. ∙

research

∙ 04/18/2019

One-dimensional Deep Image Prior for Time Series Inverse Problems

We extend the Deep Image Prior (DIP) framework to one-dimensional signal...

18 Sriram Ravula, et al. ∙

research

∙ 03/20/2019

Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes

We propose a novel method for computing exact pointwise robustness of de...

16 Matt Jordan, et al. ∙

research

∙ 02/21/2019

Quantifying Perceptual Distortion of Adversarial Examples

Recent work has shown that additive threat models, which only permit the...

10 Matt Jordan, et al. ∙

research

∙ 12/01/2018

Discrete Attacks and Submodular Optimization with Applications to Text Classification

Adversarial examples are carefully constructed modifications to an input...

0 Qi Lei, et al. ∙

research

∙ 11/26/2018

Adversarial Video Compression Guided by Soft Edge Detection

We propose a video compression framework using conditional Generative Ad...

12 Sungsoo Kim, et al. ∙

research

∙ 10/28/2018

Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models

We characterize the effectiveness of a natural and classic algorithm for...

6 Shanshan Wu, et al. ∙

research

∙ 10/28/2018

Experimental Design for Cost-Aware Learning of Causal Graphs

We consider the minimum cost intervention design problem: Given the esse...

6 Erik M. Lindgren, et al. ∙

research

∙ 07/26/2018

Entropic Latent Variable Discovery

We consider the problem of discovering the simplest latent variable that...

2 Murat Kocaoglu, et al. ∙

research

∙ 06/26/2018

The Sparse Recovery Autoencoder

Linear encoding of sparse vectors is widely popular, but is most commonl...

6 Shanshan Wu, et al. ∙

research

∙ 06/17/2018

Compressed Sensing with Deep Image Prior and Learned Regularization

We propose a novel method for compressed sensing recovery using untraine...

10 David Van Veen, et al. ∙

research

∙ 01/23/2018

From Centralized to Decentralized Coded Caching

We consider the problem of designing decentralized schemes for coded cac...

0 Yitao Chen, et al. ∙

research

∙ 12/26/2017

The Robust Manifold Defense: Adversarial Training using Generative Models

Deep neural networks are demonstrating excellent performance on several ...

0 Andrew Ilyas, et al. ∙

research

∙ 09/18/2017

Model-Powered Conditional Independence Test

We consider the problem of non-parametric Conditional Independence testi...

0 Rajat Sen, et al. ∙

research

∙ 09/06/2017

CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training

We propose an adversarial training procedure for learning a causal impli...

0 Murat Kocaoglu, et al. ∙

research

∙ 07/12/2017

Gradient Coding from Cyclic MDS Codes and Expander Graphs

Gradient Descent, and its variants, are a popular method for solving emp...

0 Netanel Raviv, et al. ∙

research

∙ 03/09/2017

Compressed Sensing using Generative Models

The goal of compressed sensing is to estimate a vector from an underdete...

0 Ashish Bora, et al. ∙

research

∙ 03/08/2017

Scalable Greedy Feature Selection via Weak Submodularity

Greedy algorithms are widely used for problems in machine learning such ...

0 Rajiv Khanna, et al. ∙

Alexandros G. Dimakis

Featured Co-authors