You are invited to a talk by Dr. Arnab Bhattacharyya hosted by the Department of Computer Science on Wednesday, April 19, virtually from 4:25 to 5:25 PM. To join us please use this Zoom link: https://iastate.zoom.us/j/96874044777.
Title: Algorithms for learning and testing high-dimensional statistical and causal relations
New local differentially private protocols for frequency and mean estimation
Speaker: Jelani Nelson
Time and Location: Monday April 3 1-2pm in 3043 Coover
Resource management significantly impacts the performance and availability of cloud infrastructure. In the first part of my talk, I will introduce my work on managing memory, cache, and power resources to boost the performance and availability of cloud infrastructure. On memory resources, we propose UH-MEM, a utility-based data placement technique for hybrid memory.
The Midwest Big Data Summer School will be held May 16th - 19th, 2022 at Iowa State University, on campus. This is an in-person event. More details will be coming soon!
Incentivized Bandit Learning under Self-Reinforcing User Preference for Online Recommender Systems
Why is it so hard to make self-driving cars? Trustworthy autonomous systems
Joseph Sifakis, Verimag Laboratory
Exploring the Security Vulnerabilities of Intelligent IoT Systems
Automated Scientific Knowledge Extraction from Massive Text Data
Novel Approaches to Preserving Utility in Privacy Enhancing Technologies
Compute-less Networking: Enabling the operation of Next-Generation Applications
Machine Learning Meets Security and Privacy: Opportunities and Challenges
Enabling Big Memory Applications with Memory Heterogeneity
Advancing and Accelerating Vetting of the Closed-source Software Ecosystem
Strengthening and Enriching Machine Learning for Cybersecurity
Securing Operating System Kernels with Fewer Shots
Multi-Objective Optimization for Big Data Mining
Toward Trustworthy Machine Learning to Understand the Genetic Basis of Phenotyped Subtypes of Alzheimer’s disease
Fostering Trustworthiness in Machine Learning: From Transparence to Robustness
Algorithmic Solutions for Socially Responsible AI
Artificial intelligence (AI) technologies have become increasingly pervasive, offering both promises and perils. In response, researchers and
organizations have been working to publish principles for the responsible use of AI. To bridge from these principles to responsible AI practice, in this talk, I will introduce
Uncertainties, Complexities and Scalable Inference: A Few Peeks at Bayesian Machine Learning
AI Security: Exploring the Vulnerabilities of Modern Deep Learning Algorithms and System
Open-World Visual Perception
'Revisiting the Role of Visual Media in Understanding a Rich Multimodal World'
'Collaborative Machine Learning via Model Fusion'
'Scalable and Learned Algorithms for Discrete Optimization'
Daniela Witten is a coauthor of the popular text Introduction to Statistical Learning by James, Witten, Hastie, and Tibshirani. Since earning her PhD at Stanford in 2010, Professor Witten has had many impressive accomplishments. At the 2018 Women in Data Science Conference, Professor Witten gave a lecture watched by 100,000 via livestream.
Abstract, via Professor Witten:
The D4 Institute at Iowa State University will host a Data Science conference on October 30th, 2021. Join us virtually to hear a keynote speech from a Research Science Manager at Amazon, to engage in a D4 Institute panel discussion on data science graduate studies, and to participate in a poster session!
*To access the meeting link, please check your email inbox. All registered attendees were sent the Zoom link on 10/29 at 10:00am from email@example.com*
Instance-Optimal Compressed Sensing via Conditional Resamplin
Presenter: Agus Sudjianto
Title: Managing Machine Learning Risk: Interpretability and Robustness
Boa is a domain-specific language and infrastructure that eases mining software repositories. Boa's infrastructure leverages distributed computing techniques to execute queries against hundreds of thousands of software projects very efficiently. Boa has existed for almost 7 years with a large user base of more than 1,200 users in all over the world.
Presenter: Laura Miller
Title: Integrate structural analysis, isoform diversity, and interferon-inductive propensity of ACE2 to predict SARS-CoV-2 susceptibility in vertebrates
Presenter: Dan Gianola
Title: David vs. Goliath: the COVID-19 epidemic in Uruguay in a regional and world context
Presenter: Walter Moss
Title: Finding and Folding Functional RNA in SARS-CoV-2
Bio: Walter Moss is an Assistant Professor in the Department of Biochemistry, Biophysics, and Molecular Biology at Iowa State University.
Presenter: Yan Wang
Title: Wasserstein subsampling: Theory and Empirical Performance
Presenter: Xiaoyun Fu
Title: Quantifying attitude of individuals in social networks
Presenter: Jiaming Qiu
Title: Nonparametric estimates for repeated densities with heterogeneous sample sizes
Presenter: Chancellor Johnstone
Title: Distribution Free Prediction Intervals
Presenter: Geoffrey Thompson
Title: A k-means based image compression method
Presenter: Mikaela Cashman
Title: The Software Engineer’s Role in Predictive Biology
Abstract: In the age of big data, predictive biology has scaled dramatically creating a community of biologists and bioinformaticians with a need for strong computational power. This talk will introduce a large open-source system aimed to meet these goals known as the Department of Energy’s Systems Biology Knowledgebase (KBase, http://kbase.us). KBase includes over 200 applications in the areas of genome assembly and annotation, sequence alignment, metabolic modeling, expression and more. There is also support for external tool integration through an SDK. KBase is designed to be open and collaborative where users can utilize public datasets, import custom data, create workflows built upon Jupyter notebooks, and share these workflows with others.
Presenter: Peter Dixon
Title: Distribution Testing and Complexity
Presenter: Dr. Jane Cleland-Huang
Title: Human-Drone Partnerships in Emergency Response
Presenter: Dr. Yuliya Lierlier
Title: Answer Set Programming and Automatic Optimization Methods in its Realm
Presenter: Eduardo Blanco
Title: Towards Deeper Natural Language Understanding
Presenter: Lee Przybylski and Nate Harding
Title: Two Challenge Problems from the Algorithms for Threat Detection Program
Presenter: Dr. Eric Hansen
Title: A New Approach to Integrating Graphical Models in Decision-Theoretic Planning
Presenter: Durga Paudyal
Title: Coupling Materials Physics with Data Science to Predict New Materials and Properties
Presenter: Gavin Nop
Title: Derivative-free Optimization
Presenter: Dr. Pavan Aduri
Topic: Simultaneous Time and Memory Efficient Algorithm for Reachability in Graphs
Presenter: Dr. Steve Holland
Topic: Big Data for nuclear power plans and creating discoverable data repositories for nondestructive evaluation
Presenter: Dr. Ranjan Maitra
Topic: Kernel-estimated Nonparametric Overlap-Based Syncytial Clustering
Presenter: Dr. Hal Schenck
Topic: Topological data analysis
Presenter: Dr. Chinmay Hedge
Topic: Theoretical aspects of neural network learning
Presenter: Bill Gallus
Presenter: Md Johirul Islam
Topic: MODE: Automated Neural Network Model Debugging via State Differential Analysis and Input Selection
Presenter: Md Johirul Islam
Topic: What Do Developers Ask About ML Libraries? A Large-scale Study Using Stack Overflow