ARO MURI Wiki

Adaptive Exploitation of Non-Commutative Multimodal Information Structure

ARMY MURI grant: W911NF-15-1-0479
ARO Program Manager: Dr. Hamid Krim

MURI Team

Prof. Yoram Bresler, University of Illinois Urbana Champaign

Co-PI's:

Prof. Todd Coleman, University of California San Diego
Prof. Alfred O. Hero, University of Michigan
Prof. Raj R. Nadakuditi, University of Michigan
Prof. Robert D. Nowak, University of Wisconsin
Prof. Maxim Raginsky, University of Illinois Urbana Champaign
Prof. Silvio Savarese, Stanford University
Prof. Vahid Tarokh, Duke University

A complete roster and web page links may be found at People.

Executive Summary

Non-commutativity is intrinsic to emerging complex sensing and processing systems. The performance of a distributed sensor network depends on the ordering or partial ordering of the sequence of information sharing actions taken across the network. Multiuser brain-computer interfaces provide directed channels of neural communication from human to machine and between humans. Understanding human activities from video requires differentiating between different ordered or partially ordered sequences of gestures and actions. Hierarchical models for signals, images, and videos, such as convolutional networks and HDP representations, are directed graphs that may link multiple layers of data types including real-valued scalars, vectors, and matrices; categorical and ordinal variables (ranks); graphs and hypergraphs; and symbolic categories with complicated spatial and temporal co-dependencies. Extracting useful information from such complex data sources is always constrained by limited resources, such as energy or computation power, limited sensing opportunity (i.e., transient visibility), and limited transmission capacity. The powerful toolboxes of convex optimization, information theory, and statistical machine learning have enabled breakthroughs in computer vision, speech recognition, and database indexing, for which algorithms can be designed offine from large amounts of training data. A grand challenge is to move beyond offine static designs to online, sequential, and adaptive designs of data collection and analysis. To do so, we must grapple with the increased design complexity associated with adaptive procedures. Principal among the reasons for increased complexity is non-commutativity of the sequence of sensing actions: the optimal action depends critically on the result of previous actions. The objective of our proposed effort is to address this challenge by developing new tools for the next generation of adaptive online sensing and processing systems.

Publications

publications: publications resulting from this program.

Annual Review

The 4th annual review of the MURI will take place on Oct 21 2020.

The meeting will be virtual and will take place in the Zoom room https://umich.zoom.us/j/97652740954.

The high level agenda is below. All times are EDT.

10:00 - Introduction (Bresler, Hero and Krim).

10:05 - MURI overview of accomplishments (Al and Yoram)

10:30 - Technical talks

12:00 - East coast lunch break & Poster Session (in Zoom breakout rooms)

12:30 - Technical talks

14:00 - West coast lunch break & Poster Session (in Zoom breakout rooms)

14:30 - Technical talks

16:00 - Wrapup (Al and Yoram)

16:15 - Govt Caucus

17:30 - Adjourn

Detailed Technical Agenda

10am Overview of MURI accomplishments

Overview (Al Hero and Yoram Bresler) Slides

10:30am Thrust 1 - Non-commutative information: representation of uncertainty

Overview of area (Vahid Tarokh) Slides

Presentations: (Moderator: Al Hero)

Duke post-doc Deep neural compression Slides Highlight slide
Duke post-doc Fisher-autoencoder Slides Highlight Slide
UM grad student Space-Time Adaptive Processing (STAP) with low sample support Slides Highlight slide
UIUC co-PI Neural nets, controlled diffusions, and entropic optimal transport Slides Recorded presentation Highlight slide

12pm Breakout sessions I: students will be available for Q&A and to present highlights of their work

Session 1: Q&A for students who presented in Thrust session 1. Moderator Vahid Tarokh
Session 2: Preview of talks for students presenting in Thrust session 2. Moderator Todd Coleman
Session 3: Preview of talks for students presenting in Thrust session 3. Moderator Silvio Savarese

12:30pm Thrust 2: Fusion: multimodal learning in high dimensions

Overview of area (Todd Coleman) Slides

Presentations: (Moderator: Raj Nadakuditi)

UM grad student SyGlasso graphical models and clustering Slides Highlight slide
Stanford post-doc JRDB - the JackRabbot Dataset and Benchmark Slides Highlight slide
UIUC Co-PI Robustness in deep learning-based image reconstruction Slides Highlight slide
UM grad student Fusion from fragments Slides Highlight slide
UCSD grad student Regularized Wasserstein clustering Slides Highlight slide

2pm Breakout sessions II: students will be available for Q&A and to present highlights of their work

Session 1: Q&A for students who presented in Thrust session 1. Moderator Al Hero
Session 2: Q&A for students who presented in Thrust session 2. Moderator Yoram Bresler
Session 3: Preview of talks for students presenting in Thrust session 3. Moderator Rob Nowak

2:30pm Thrust 3: Non-commutative information gathering and decision making

Overview of area (Rob Nowak) Slides

Presentations: (Moderator: Silvio Savarese)

Stanford post-doc <Claudia D’Arpino> Robot navigation in constrained pedestrian environments using RL Slides Highlight slide
UM grad student Robust elastic computing Slides Highlight slide
UW grad student A Call to All Good Arms Slides Highlight slide
UW post-doc Generalized Chernoff sampling Slides Highlight slide