Search
Now showing items 1-10 of 52
Learning Submodular Functions
(Georgia Institute of Technology, 2009)
This paper considers the problem of learning submodular functions. A problem instance consists
of a distribution on {0,1}[superscript n] and a real-valued function on {0,1}[superscript n] that is non-negative, monotone ...
Expectation-Oriented Framework for Automating Approximate Programming
(Georgia Institute of Technology, 2013)
This paper describes ExpAX, a framework for automating approximate programming based on programmer-specified error expectations. Three components constitute ExpAX: (1) a programming
model based on a new kind of program ...
Incremental Light Bundle Adjustment for Robotics Navigation
(Georgia Institute of Technology, 2013-11)
This paper presents a new computationally-efficient method for vision-aided navigation (VAN) in autonomous robotic applications. While many VAN approaches
are capable of processing incoming visual observations, incorporating ...
Efficient and principled robot learning: Theory and algorithms
(Georgia Institute of Technology, 2020-01-07)
Roboticists have long envisioned fully-automated robots that can operate reliably in unstructured environments. This is an exciting but extremely difficult problem; in order to succeed, robots must reason about sequential ...
Convergence in min-max optimization
(Georgia Institute of Technology, 2020-04-20)
Min-max optimization is a classic problem with applications in constrained optimization, robust optimization, and game theory. This dissertation covers new convergence rate results in min-max optimization. We show that the ...
Accelerating program analyses by cross-program training
(Georgia Institute of Technology, 2016-11-30)
Practical programs share large modules of code. However, many program analyses are ineffective at reusing analysis results for shared code across programs. We present POLYMER, an analysis optimizer to address this problem. ...
Variations of Submodularity and Diversity: from Robust Optimization to Markov Chains
(2017-09-25)
The combinatorial concept of submodular set functions has proved to be a very useful discrete structure for optimization in machine learning and its applications. In this talk, I will show recent work on generalizations ...
Optimization-driven emergence of deep hierarchies with applications in data mining and evolution
(Georgia Institute of Technology, 2018-11-09)
It is well known that many complex systems, in both nature and technology, exhibit hierarchical modularity: smaller modules, each of them providing a certain function, are used within larger modules that perform more complex ...
From Minimum Cut to Submodular Minimization: Leveraging the Decomposable Structure
(2016-10-17)
Submodular function minimization is a fundamental optimization problem that arises in several applications in machine learning and computer vision. The problem is known to be solvable in polynomial time, but general purpose ...
Using Knowledge to Optimally Achieve Coordination in Distributed Systems
(Georgia Institute of Technology, 1993)
The problem of coordinating the actions of individual processors is
fundamental in distributed computing. Researchers have long endeavored
to find efficient solutions to a variety of problems involving
coordination. ...