Logo: University of Southern California

Events Calendar



Select a calendar:



Filter June Events by Event Type:


SUNMONTUEWEDTHUFRISAT

Events for June 20, 2024

  • Ph.D. Thesis Defense - Yuan Meng

    Thu, Jun 20, 2024 @ 02:00 PM - 04:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    PhD Thesis Defense - Yuan Meng    
     
    Committee Members: Prof Viktor K. Prasanna (Chair), Prof. Bhaskar Krishnamachari, Prof. Yue Zhao    
     
    Title: Accelerating Reinforcement Learning using Heterogeneous Platforms: Co-Designing Hardware, Algorithm, and System Solutions    
     
    Abstract: Reinforcement Learning (RL) is an area of AI that constitutes a wide range of algorithms, enabling autonomous agents to learn optimal decisions through online environment interactions, data collection, and training. Recently, certain categories of RL algorithms have witnessed widespread adoption due to their generalizability and reliability, including model-free RL based on policy/value optimizations and model-based RL using Monte Carlo Tree Search. General-purpose processors fail to optimally achieve efficient execution speed for RL due to the intrinsic heterogeneous characteristics among various RL primitives and algorithms. Optimized acceleration systems that exploit heterogeneity across different architectures to support the variations of compute kernels and memory characteristics in RL are crucial to fast and efficient application development.   In this dissertation, we develop acceleration frameworks for two key categories of RL algorithms, i.e., model-free Deep RL, and model-based RL using Monte Carlo Tree Search (MCTS). We implement these frameworks by addressing two objectives: 1. We develop algorithm-hardware co-optimized accelerators for the fundamental primitives in the key categories of RL algorithms. This includes inference and training of DNN policy models, as well as dynamic tree-based operations in MCTS. 2. We create portable system solutions that identify the optimal primitive scheduling, mapping, and design configurations onto heterogeneous devices based on the task dependency, compute, and memory characteristics of the target RL algorithms.   Experiments on various platforms consisting of interconnected CPUs, FPGAs, and GPUs showcase superior performance enhancements across diverse models, algorithms, hardware platforms, and benchmark environments compared to state-of-the-art RL libraries.   
     
    Bio: Yuan Meng is a fifth-year PhD candidate in Computer Engineering, advised by Professor Viktor K. Prasanna. She obtained her BS degree in electrical and computer engineering at Rensselaer Polytechnic Institute. Her research interests include parallel computing, deep learning acceleration, heterogeneous computing, and reinforcement learning.     
     
    Date: Thursday, June 20th, 2024
    Time: 2pm
    Location:  EEB 132
    Zoom Link: https://usc.zoom.us/j/8629150353  

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

    Audiences: Everyone Is Invited

    Contact: CS Events

    Event Link: ://usc.zoom.us/j/8629150353

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File
  • PhD Dissertation Defense - Ang Li

    Thu, Jun 20, 2024 @ 02:00 PM - 03:30 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Title: Revisiting FastMap: New Applications
     
    Date: Thursday, June 20th, 2024 - 2:00p - 3:30p
     
    Location: SAL 213
     
    Committee Members: T. K. Satish Kumar (Chair), John Carlsson, Emilio Ferrara, Sven Koenig, and Aiichiro Nakano
     
    Abstract: FastMap was first introduced in the Data Mining community for generating Euclidean embeddings of complex objects. In this talk, I will first generalize FastMap to generate Euclidean embeddings of graphs in near-linear time: The pairwise Euclidean distances approximate a desired graph-based distance function on the vertices. I will then apply the graph version of FastMap to efficiently solve various graph-theoretic problems of significant interest in AI: including facility location, top-K centrality computations, community detection and block modeling, and graph convex hull computations. I will also present a novel learning framework, called FastMapSVM, by combining FastMap and Support Vector Machines. I will then apply FastMapSVM to predict the satisfiability of Constraint Satisfaction Problems and to classify seismograms in Earthquake Science.
     
    Zoom Link: https://usc.zoom.us/j/92402869565?pwd=L0dwc0xRZVNrT3UrQWZCcERmVlBqQT09

    Location: Henry Salvatori Computer Science Center (SAL) - 213

    Audiences: Everyone Is Invited

    Contact: Ang Li

    Event Link: https://usc.zoom.us/j/92402869565?pwd=L0dwc0xRZVNrT3UrQWZCcERmVlBqQT09

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File