SDS Seminar Series – Adam Klivans, University of Texas at Austin
Oct
16
2026
Oct
16
2026
Description
The Fall 2026 SDS Seminar Series continues on October 16th from 2:00 p.m. to 3:00 p.m. with Adam Klivans (Director of AI Initiatives, School of Computing, University of Texas at Austin). This event is in-person in the Avaya Room (POB 2.302).
Title: Efficient Algorithms for Reliable Machine Learning
Abstract: Algorithms for supervised learning typically require some sort of distributional assumption (e.g., Gaussianity), in contrast to the traditional worst-case analysis paradigm from theoretical computer science. This leads to algorithms that succeed only under hard-to-verify assumptions, undermining the very notion of provable correctness. In this talk, I will describe new learning models where an algorithm either certifies the accuracy of its output classifier or abstains when a distributional assumption has been violated. We will show how this framework leads to the first provably efficient algorithms for learning with distribution shift (with no assumptions on the target domain) and also introduces new techniques that resolve longstanding open problems in supervised learning with contamination.
Other Events in This Series
Sep
5
2025
SDS Seminar Series – Sarah Coleman, University of Texas at Austin
A Linear Mixed Effects Model for Evaluating Synthetic Gene Circuits
2:00 pm – 3:00 pm • In Person
Speaker(s): Sarah Coleman
Sep
12
2025
SDS Seminar Series – Lydia Lucchesi, University of Texas at Austin
Visual Documentation for Data Preprocessing in R and Python
2:00 pm – 3:00 pm • In Person
Speaker(s): Lydia Lucchesi
Sep
19
2025
SDS Seminar Series – Tuan Pham, University of Texas at Austin
Time-uniform Bounds for Iterated Algorithms
2:00 pm – 3:00 pm • In Person
Speaker(s): Tuan Pham
Sep
26
2025
SDS Seminar Series - Ryan Giordano, University of California, Berkeley
Local Weighting--Based Diagnostics for Bayesian Multilevel Regression with Poststratification
2:00 pm – 3:00 pm • In Person
Speaker(s): Ryan Giordano
Oct
3
2025
SDS Seminar Series – Rafael Campello de Alcantara, University of Texas at Austin
Searching for Parallel Trends: A Decision Tree Algorithm for Discovering Conditional Diff-in-Diff Estimators
2:00 pm – 3:00 pm • In Person
Speaker(s): Rafael Campello de Alcantara
Oct
10
2025
SDS Seminar Series – Michele Guindani, University of California, Los Angeles
Embracing Heterogeneity: Bayesian Clustering Methods for Neuroscience Data
2:00 pm – 3:00 pm • In Person
Speaker(s): Michele Guindani
Oct
17
2025
SDS Seminar Series – Wenyi Wang, MD Anderson Cancer Center
Deciphering Tumor Heterogeneity for Benefits from Immunotherapy in Cancer
2:00 pm – 3:00 pm • In Person
Speaker(s): Wenyi Wang
Oct
24
2025
SDS Seminar Series - Jonathan Huggins, Boston University
Robust Model Selection for Discovery of Latent Mechanistic Processes
2:00 pm – 3:00 pm • In Person
Speaker(s): Jonathan Huggins
Oct
31
2025
SDS Seminar Series – Max Goplerud, University of Texas at Austin
Generalized Bilinear Mixed Models and Variational Inference
2:00 pm – 3:00 pm • In Person
Speaker(s): Max Goplerud
Nov
7
2025
SDS Seminar Series – Jeffrey Miller, Harvard University
Bayesian Model Criticism Using Uniform Parametrization Checks
2:00 pm – 3:00 pm • In Person
Speaker(s): Jeffrey Miller
