Search Results for author: George Atia

Found 22 papers, 0 papers with code

Model-Free Robust Average-Reward Reinforcement Learning

no code implementations17 May 2023 Yue Wang, Alvaro Velasquez, George Atia, Ashley Prater-Bennette, Shaofeng Zou

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs.

Q-Learning reinforcement-learning

On the Robustness of AlphaFold: A COVID-19 Case Study

no code implementations10 Jan 2023 Ismail Alkhouri, Sumit Jha, Andre Beckus, George Atia, Alvaro Velasquez, Rickard Ewetz, Arvind Ramanathan, Susmit Jha

To measure the robustness of the predicted structures, we utilize (i) the root-mean-square deviation (RMSD) and (ii) the Global Distance Test (GDT) similarity measure between the predicted structure of the original sequence and the structure of its adversarially perturbed version.

Protein Folding

Robust Average-Reward Markov Decision Processes

no code implementations2 Jan 2023 Yue Wang, Alvaro Velasquez, George Atia, Ashley Prater-Bennette, Shaofeng Zou

We derive the robust Bellman equation for robust average-reward MDPs, prove that the optimal policy can be derived from its solution, and further design a robust relative value iteration algorithm that provably finds its solution, or equivalently, the optimal robust policy.

Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning

no code implementations9 Jul 2021 Taylor Dohmen, Noah Topper, George Atia, Andre Beckus, Ashutosh Trivedi, Alvaro Velasquez

The success of reinforcement learning in typical settings is predicated on Markovian assumptions on the reward signal by which an agent learns optimal policies.

Decision Making reinforcement-learning +1

Controller Synthesis for Omega-Regular and Steady-State Specifications

no code implementations5 Jun 2021 Alvaro Velasquez, Ismail Alkhouri, Andre Beckus, Ashutosh Trivedi, George Atia

Given a Markov decision process (MDP) and a linear-time ($\omega$-regular or LTL) specification, the controller synthesis problem aims to compute the optimal policy that satisfies the specification.

A Multi-criteria Approach for Fast and Outlier-aware Representative Selection from Manifolds

no code implementations12 Mar 2020 Mahlagha Sedghi, George Atia, Michael Georgiopoulos

The problem of representative selection amounts to sampling few informative exemplars from large datasets.

Rediscovering Deep Neural Networks Through Finite-State Distributions

no code implementations26 Sep 2018 Amir Emad Marvasti, Ehsan Emad Marvasti, George Atia, Hassan Foroosh

We propose a new way of thinking about deep neural networks, in which the linear and non-linear components of the network are naturally derived and justified in terms of principles in probability theory.

Scalable and Robust Community Detection with Randomized Sketching

no code implementations25 May 2018 Mostafa Rahmani, Andre Beckus, Adel Karimian, George Atia

Uniform random node sampling is shown to improve the computational complexity over clustering of the full graph when the cluster sizes are balanced.

Clustering Community Detection +3

Data Dropout in Arbitrary Basis for Deep Network Regularization

no code implementations4 Dec 2017 Mostafa Rahmani, George Atia

An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset.

Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery

no code implementations ICML 2017 Mostafa Rahmani, George Atia

To the best of our knowledge, this is the first provable robust PCA algorithm that is simultaneously non-iterative, can tolerate a large number of outliers and is robust to linearly dependent outliers.

Innovation Pursuit: A New Approach to the Subspace Clustering Problem

no code implementations ICML 2017 Mostafa Rahmani, George Atia

Remarkably, the proposed approach can provably yield exact clustering even when the subspaces have significant intersections.


Subspace Clustering via Optimal Direction Search

no code implementations12 Jun 2017 Mostafa Rahmani, George Atia

This letter presents a new spectral-clustering-based approach to the subspace clustering problem.

Clustering Face Clustering

Spatial Random Sampling: A Structure-Preserving Data Sketching Tool

no code implementations9 May 2017 Mostafa Rahmani, George Atia

Random column sampling is not guaranteed to yield data sketches that preserve the underlying structures of the data and may not sample sufficiently from less-populated data clusters.


Low Rank Matrix Recovery with Simultaneous Presence of Outliers and Sparse Corruption

no code implementations7 Feb 2017 Mostafa Rahmani, George Atia

Our approach hinges on the sparse approximation of a sparsely corrupted column so that the sparse expansion of a column with respect to the other data points is used to distinguish a sparsely corrupted inlier column from an outlying data point.

Robust and Scalable Column/Row Sampling from Corrupted Big Data

no code implementations18 Nov 2016 Mostafa Rahmani, George Atia

Conventional sampling techniques fall short of drawing descriptive sketches of the data when the data is grossly corrupted as such corruptions break the low rank structure required for them to perform satisfactorily.


Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis

no code implementations15 Sep 2016 Mostafa Rahmani, George Atia

As inliers lie in a low dimensional subspace and are mostly correlated, an inlier is likely to have strong mutual coherence with a large number of data points.

Innovation Pursuit: A New Approach to Subspace Clustering

no code implementations2 Dec 2015 Mostafa Rahmani, George Atia

This paper presents a new approach dubbed Innovation Pursuit (iPursuit) to the problem of subspace clustering using a new geometrical idea whereby subspaces are identified based on their relative novelties.

Clustering Face Clustering

Formalized Quantum Stochastic Processes and Hidden Quantum Models with Applications to Neuron Ion Channel Kinetics

no code implementations31 Oct 2015 Alan Paris, George Atia, Azadeh Vosoughi, Stephen Berman

A new class of formal latent-variable stochastic processes called hidden quantum models (HQM's) is defined in order to clarify the theoretical foundations of ion channel signal processing.

Randomized Robust Subspace Recovery for High Dimensional Data Matrices

no code implementations21 May 2015 Mostafa Rahmani, George Atia

This paper explores and analyzes two randomized designs for robust Principal Component Analysis (PCA) employing low-dimensional data sketching.

Vocal Bursts Intensity Prediction

High Dimensional Low Rank plus Sparse Matrix Decomposition

no code implementations1 Feb 2015 Mostafa Rahmani, George Atia

In this paper, a scalable subspace-pursuit approach that transforms the decomposition problem to a subspace learning problem is proposed.

Clustering Small Data Image Classification +1

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