Get to know your Duncan Hall neighbors! Join Rice CS for coffee & a series of talks on algorithms & machine learning at Rice.
Coffee & Food for Thought: Algorithms & ML
Presenter: Yiyuan Lee, Rice CS Ph.D. student advised by Prof. Lydia Kavraki
Title: The Planner Optimization Problem: Formulations and Frameworks
Wed, March 29, 2023, 2-3pm Central
Duncan Hall 1049
Abstract: Identifying internal parameters for planning is crucial to maximizing the performance of a planner. However, automatically tuning internal parameters which are conditioned on the problem instance is especially challenging. A recent line of work focuses on extremely general learning methods which can learn highly effective generators with very little assumptions on the internals of the planner. However, they lack a consistent problem formulation and software framework. This work proposes the unified planner optimization problem (POP) formulation, along with the Open Planner Optimization Framework (OPOF), a highly extensible software framework to specify and to solve these problems in a reusable manner.
Bio: Yiyuan Lee is a second-year Ph.D student at Rice University advised by Lydia Kavraki. He is broadly interested in integrating learning and simulation for planning in robotics. His works have been published in top robotics conferences and journals such as RSS, IEEE ICRA, and IEEE RA-L.
Past Speakers:
Mar 8, 2023: Zhiwei Zhang, A Continuous-Optimization-Based Approach for Hybrid Boolean Satisfiability
Mar 1, 2023: T. Mitchell Roddenberry, Probabilistic approaches to taming network data
Feb 22, 2023: J. Lyle Kim, When is Momentum Extragradient Optimal? A Polynomial-Based Analysis
Feb 15, 2023: Cameron R. Wolfe, Perspectives on Hyperparameter Scheduling for Deep Learning
Feb 8, 2023: Shiqian Ma, A Gentle Introduction to Bilevel Optimization
Feb 1, 2023: Vicente Ordóñez Román, Instance-level Image Recognition with Transformers
Jan 25, 2023: Nai-Hui Chia, Quantum-inspired matrix arithmetic framework for dequantizing quantum machine learning
Jan 18, 2023: Jingfeng Wu, A Fine-Grained Characterization for the Implicit Regularization of SGD in Least Square Problems
Jan 11, 2023, Thamar Solorio, Data Augmentation in Sequence Labelling Tasks
Jan 4, 2023: Samson Zhou, Theoretical Foundations of Modern Data Science
Nov 30, 2022: Sebastian Perez-Salazar, IID Prophet Inequalities with Limited Flexibility
Nov 16, 2022: Anshumali Shrivastava, Probabilistic Hash Functions and Hash Tables: A New Paradigm for Efficient AI Training and Inference
Nov 2, 2022: César A. Uribe, Hyperfast Second-Order Local Solvers for Efficient Statistically Preconditioned Distributed Optimization
Oct 26, 2022: Xia (Ben) Hu, Towards Effective & Efficient Interpretation of Deep Neural Networks: Algorithms & Applications
Oct 19, 2022: Vaibhav Unhelkar, Enabling Humans and Robots to Predict the Other’s Behavior from Small Datasets
Oct 12, 2022: Arlei Silva, Link Prediction with Autocovariance