Select a calendar:
Filter March Events by Event Type:
Events for March 25, 2021
-
CS Colloquium: Michał Dereziński (University of California, Berkeley) - Bridging algorithmic and statistical randomness in machine learning
Thu, Mar 25, 2021 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: MichaÅ DereziÅski , University of California, Berkeley
Talk Title: Bridging algorithmic and statistical randomness in machine learning
Series: CS Colloquium
Abstract: Randomness is a key resource in designing efficient algorithms, and it is also a fundamental modeling framework in statistics and machine learning. Methods that lie at the intersection of algorithmic and statistical randomness are at the forefront of modern data science. In this talk, I will discuss how statistical assumptions affect the bias-variance trade-offs and performance characteristics of randomized algorithms for, among others, linear regression, stochastic optimization, and dimensionality reduction. I will also present an efficient algorithmic framework, called joint sampling, which is used to both predict and improve the statistical performance of machine learning methods, by injecting carefully chosen correlations into randomized algorithms.
In the first part of the talk, I will focus on the phenomenon of inversion bias, which is a systematic bias caused by inverting random matrices. Inversion bias is a significant bottleneck in parallel and distributed approaches to linear regression, second order optimization, and a range of statistical estimation tasks. Here, I will introduce a joint sampling technique called Volume Sampling, which is the first method to eliminate inversion bias in model averaging. In the second part, I will demonstrate how the spectral properties of data distributions determine the statistical performance of machine learning algorithms, going beyond worst-case analysis and revealing new phase transitions in statistical learning. Along the way, I will highlight a class of joint sampling methods called Determinantal Point Processes (DPPs), popularized in machine learning over the past fifteen years as a tractable model of diversity. In particular, I will present a new algorithmic technique called Distortion-Free Intermediate Sampling, which drastically reduced the computational cost of DPPs, turning them into a practical tool for large-scale data science.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: MichaÅ DereziÅski is a postdoctoral fellow in the Department of Statistics at the University of California, Berkeley. Previously, he was a research fellow at the Simons Institute for the Theory of Computing (Fall 2018, Foundations of Data Science program). He obtained his Ph.D. in Computer Science at the University of California, Santa Cruz, advised by professor Manfred Warmuth, where he received the Best Dissertation Award for his work on sampling methods in statistical learning. MichaÅ's current research is focused on developing scalable randomized algorithms with robust statistical guarantees for machine learning, data science and optimization. His work on reducing the cost of interpretability in dimensionality reduction received the Best Paper Award at the Thirty-fourth Conference on Neural Information Processing Systems. More information is available at: https://users.soe.ucsc.edu/~mderezin/.
Host: David Kempe
Audiences: By invitation only.
Contact: Assistant to CS chair
-
Undergraduate Advisement Drop-in Hours
Thu, Mar 25, 2021 @ 01:30 PM - 02:30 PM
Thomas Lord Department of Computer Science
Workshops & Infosessions
Do you have a quick question? The CS advisement team will be available for drop-in live chat advisement for declared undergraduate students in our four majors during the spring semester on Tuesdays, Wednesdays, and Thursdays from 1:30pm to 2:30pm Pacific Time. Access the live chat on our website at: https://www.cs.usc.edu/chat/
Location: Online
Audiences: Undergrad
Contact: USC Computer Science
-
Career Conversations
Thu, Mar 25, 2021 @ 05:00 PM - 05:30 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Learn about Career Connections events, activities, and recruitment strategies to find internship and full-time positions. This session will be held with Assistant Director, Brittany Chu.
RSVP to this workshop on Viterbi Career Gateway.Location: Zoom
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
USC Young Alumni SCuppers - Engineering
Thu, Mar 25, 2021 @ 05:00 PM - 06:00 PM
Viterbi School of Engineering Alumni
Workshops & Infosessions
Join fellow recent graduates for a virtual Young Alumni SCupper on the topic of Engineering!
During the SCuppers, young alumni will have the opportunity to network and learn industry advice from previous generations of Trojans. Traditionally held over a meal, alumni hosts share their Trojan stories, discuss their professional journeys, and answer career questions. SCuppers are a great way to make lasting connections with fellow alumni and expand one's Trojan Network.
Each SCuppers is hosted by impressive alumni working in different aspects of the engineering industry.
Mark Sahlin MSEE '86, a Model Based System Development Champion at John Deere, will be leading the conversation and sharing his expertise in the engineering world.
This is a great opportunity to expand your Trojan Network and learn how to excel in your career. Fight On!
Click here to register!Audiences: Everyone Is Invited
Contact: Kristy Ly
-
FBI Cyber and Counterintelligence Needs You!
Thu, Mar 25, 2021 @ 06:00 PM - 07:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
The FBI uses scientific analysis and technical skills to help keep the nation safe. At the FBI, every STEM opportunity offers a career like no other. STEM professionals at the FBI have opportunities to work with advanced technologies to address unique investigative and intelligence challenges not found in the private sector. Their expertise applies to forensic science, computer technology, cyber security, electronic surveillance, biometrics, encryption and more. STEM professionals also have opportunities to experience a variety of careers within the FBI, such as becoming a Computer Scientist, Data Analyst, Special Agent, or Intelligence Analyst.
This Trojan Talk will take a look at the FBI's Cyber and Counterintelligence programs and why advanced STEM major graduates are needed to protect the nation.
To RSVP: Viterbi Career Gateway > Events > Information SessionsAudiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
Young Alumni SCupper - Engineering
Thu, Mar 25, 2021 @ 06:00 PM - 07:00 PM
Viterbi School of Engineering Alumni
Workshops & Infosessions
Join fellow recent graduates for a virtual Young Alumni SCupper on the topic of Engineering!
During the SCuppers, young alumni will have the opportunity to network and learn industry advice from previous generations of Trojans. Traditionally held over a meal, alumni hosts share their Trojan stories, discuss their professional journeys, and answer career questions. SCuppers are a great way to make lasting connections with fellow alumni and expand one's Trojan Network.
Each SCuppers is hosted by impressive alumni working in different aspects of the engineering industry.
Carl Sarrazolla '84, Enterprise Data Architect at Lamb Weston, will be leading the conversation and sharing his expertise in the engineering world.
This is a great opportunity to expand your Trojan Network and learn how to excel in your career. Fight On!
Click here to register!Audiences: Everyone Is Invited
Contact: Kristy Ly
-
Trojan Talk | Tencent 2021 Internship Program Info Session
Thu, Mar 25, 2021 @ 07:00 PM - 08:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Join this Trojan Talk with Tencent! This session will be delivered in Chinese.
We will Focus on how to be fully prepared for Tencent internship application and some interview tips for engineering students. HR from Global Talent Acquisition at Tencent will share details on opportunities from Tencent.
We would also like to welcome students from USC Viterbi School of engineering to sign up for our Tech Talk held in April through this event. Speakers such as the head of Tencent AI Lab will be invited to share some advanced technology and interview tips to our students during the talk.
View Details in Viterbi Career Gateway > Events > Information Sessions
Our internship program are mainly opened to students who will graduate after September,2021. For full-time positions, students who graduate from September,2020 to August,2021 are welcomed.
We could offer Visa sponsorship if needed. All Engineering majors from Viterbi (Bachelor, Master or PHD) are welcomed, especially students from Computer Science Major (General CS, Data Science, Game Development, Security, Network, Software Engineering, Robotics, Multimedia, High Performance Computing, Artificial Intelligence, Scientist and Engineers).
For our opening positions in Chinese mainland, please find out more on: https://mp.weixin.qq.com/s/3RfBwTQ5eaOdrbX_ngxBYA
For positions in other countries and regions, please apply on https://careers.tencent.com/en-us/campusrecruit.html .Location: Online
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections