- All Categories
- Featured Events
- Alumni
- Application Deadline
- Arts
- Campus Discourse
- Careers
- BU Central
- Center for the Humanities
- Charity & Volunteering
- Kilachand Center
- Commencement
- Conferences & Workshops
- Diversity & Inclusion
- Examinations
- Food & Beverage
- Global
- Health & Wellbeing
- Keyword Initiative
- Lectures
- LAW Community
- Meetings
- Orientation
- Other Events
- Religious Services & Activities
- Special Interest to Women
- Sports & Recreation
- Social Events
- Study Abroad
- Weeks of Welcome
- Moments In Time8:00 am
- IS&T RCS Tutorial - Introduction to Python, Part Two10:00 am
- Hot Chocolate Day 11:00 am
- ECE/BME Seminar Speaker - Zohngming Liu11:00 am
- ECE Seminar: Zhongming Liu, Purdue University 11:00 am
- Silence Practice12:00 pm
- Book Seminar: “Climate Actions: Transformative Mechanisms for Social Mobilisation”12:00 pm
- IS&T RCS Tutorial - Graphics Using Base R Packages12:15 pm
- David Clough: The Challenge of Christian Animal Ethics12:15 pm
- Bioinformatics Sponsored Systems Biology Seminar12:45 pm
- SE PhD Prospectus Defense of Arman Karimian1:00 pm
- OPT Information Session for LLMs1:00 pm
- IS&T RCS Tutorial - Managing Projects on the SCC for LPIs2:30 pm
- Tea Time: Winter Break Reflections3:30 pm
- Scalable, reliable Bayesian inference via approximate likelihoods and random features (Jonathan Huggins - Harvard University)4:00 pm
- Girl Scout Cookies! 4:30 pm
- Mind, Body, and Spirit Yoga5:00 pm
- Exam Prep and Study Skills Workshop5:00 pm
- Monthly Idea Night 5:30 pm
- Monthly Idea Night at the BUild Lab5:30 pm
- Dance Theatre Group- First Meeting of Spring 20196:00 pm
- BU Wheelock Public Dialogue Series: Educating Emergent Bilingual Learners with Disabilities6:00 pm
- Faculty Recital: Bayla Keyes, violin8:00 pm
Scalable, reliable Bayesian inference via approximate likelihoods and random features (Jonathan Huggins - Harvard University)
Data analysis for decision-making in areas such as medicine, economics, environmental science, and computer security commonly share two features: (1) there are vast quantities of data available, so the inference algorithm used for a data analysis must to work at scale, and (2) the safety-critical and high-impact nature of the decisions involved makes it crucial that the results of the analysis are reliable. Therefore, an inference algorithm need to satisfy two competing goals: scalability and reliability. I consider the Bayesian approach to inference because it provides a framework for coherent modeling of our prior beliefs about how the data was generated and representations of uncertainty about inferential conclusions. I develop two approaches to scalable, reliable Bayesian inference. First, I present an approximate likelihood-based framework for developing scalable inference algorithms with a priori guarantees on accuracy in terms of Wasserstein distance. One of my resulting algorithms scales to tens of millions of observations while reducing computation and memory requirements by two to three orders of magnitude. Second, I consider a complementary approach that is applicable to the many heuristic, yet empirically effective, scalable inference algorithms in wide use. The key idea is to validate the output of an inference algorithm to check whether it is trustworthy. I introduce the first validation method applicable to modern scalable algorithms that provides theoretical guarantees and is computationally efficient, opening up the possibility of using these heuristic algorithms in a wide range of high-impact settings.
When | 4:00 pm to 5:00 pm on Thursday, January 31, 2019 |
---|---|
Location | MCS, Room 180, 111 Cummington Mall |