Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for April 11, 2023
-
PhD Thesis Defense - Hikaru Ibayashi
Tue, Apr 11, 2023 @ 09:00 AM - 10:30 AM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Defense - Hikaru Ibayashi
Title:
Sharpness Analysis of Neural-networks for Physics Simulation
Committee members:
Prof. Aiichiro Nakano (Chair), Prof. Yan Liu, Prof. Paulo Branicio (Department of Chemical Engineering and Materials Science)
Abstract:
Deep learning has attracted significant attention in recent years due to its remarkable achievements in various applications. However, building effective deep neural networks requires making crucial design choices such as the network architecture, regularization, optimization, and hyperparameter tuning.
In this dissertation, we focus on the concept of ``sharpness'' of neural networks,
which refers to neural networks' sensitivity against perturbation on weight parameters. We argue that sharpness is not only a theoretical notion but also has practical use cases that can lead to better generalization and robustness of neural models.
A major theoretical challenge of defining and measuring sharpness is its scale-sensitivity, i.e., the fact that sharpness can change to the scale transformation of neural networks. In this thesis, we propose a novel definition of sharpness that overcomes this limitation, with provable scale-invariance and extensive empirical validation. By analyzing the relationship between sharpness and model performance, We show how my definition can provide a more objective and accurate characterization of sharpness.
Another open question in the sharpness analysis is how training algorithms for machine learning models regularize sharpness. In this dissertation, we answer this question by showing that existing training algorithm methods regularize sharpness through what can be called "escaping" behavior, where the optimization process avoids sharp regions in the parameter space. This new explanation demystifies the connection between sharpness and training algorithms, paving the way for more effective and principled approaches to machine learning.
Finally, we demonstrate the practical benefits of sharpness regularization for physics simulations. We show that neural networks with small sharpness achieve high-fidelity fluid simulation and molecular dynamics. These findings include the significant implication that sharpness is not just a mathematical notion but also a practical tool for building physics-informed neural networks.
Location: Seaver Science Library (SSL) - 104
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
-
CS Colloquium: Ruishan Liu (Stanford University) - Machine learning for precision medicine
Tue, Apr 11, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ruishan Liu, Stanford University
Talk Title: Machine learning for precision medicine
Series: CS Colloquium
Abstract: Toward a new era of medicine, our mission is to benefit every patient with individualized medical care. This talk explores how machine learning can make precision medicine more effective and diverse. I will first discuss Trial Pathfinder, a computational framework to optimize clinical trial designs (Liu et al. Nature 2021). Trial Pathfinder simulates synthetic patient cohorts from medical records, and enables inclusive criteria and data valuation. In the second part, I will discuss how to leverage large real-world data to identify genetic biomarkers for precision oncology (Liu et al. Nature Medicine 2022), and how to use language models and causal inference to form individualized treatment plans.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Ruishan Liu is a postdoctoral researcher in Biomedical Data Science at Stanford University, working with Prof. James Zou. She received her PhD in Electrical Engineering at Stanford University in 2022. Her research lies in the intersection of machine learning and applications in human diseases, health and genomics. She was the recipient of Stanford Graduate Fellowship, and was selected as the Rising Star in Data Science by University of Chicago, the Next Generation in Biomedicine by Broad Institute, and the Rising Star in Engineering in Health by Johns Hopkins University and Columbia University. She led the project Trial Pathfinder, which was selected as Top Ten Clinical Research Achievement in 2022 and Finalist for Global Pharma Award in 2021.
Host: Yan Liu
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
