Course Schedule

This page will be updated regularly. Check back often.

Meeting	Date	Topic and Materials
1	F 09/11	Course Overview + Intro to Calibration Please fill out this short Google Form You should have an invitation to the course Slack Materials: notes, slides Interesting Reading: Aaron Roth, Uncertain: Modern Topics in Uncertainty Estimation Dean Foster and Rakesh Vohra, Asymptotic Calibration Sergiu Hart, Calibrated Forecasts: The Minimax Proof
2	T 09/15	Measures of Calibration Guest Lecture by Lunjia Hu Materials: notes, slides Interesting Reading: Jarosław Błasiok, Parikshit Gopalan, Lunjia Hu, and Preetum Nakkiran, A Unifying Theory of Distance from Calibration Parikshit Gopalan and Lunjia Hu, Calibration through the Lens of Indistinguishability Lunjia Hu, From Convex Analysis to Learning, Prediction, and Elicitation: Lecture 9, Section 2
3	F 09/18	Calibration and Decision Making Guest Lecture by Lunjia Hu Materials: notes, slides Interesting Reading: Lunjia Hu and Yifan Wu, Calibration Error for Decision Making Konstantina Bairaktari, Lunjia Hu, Huy L. Nguyen, and Jonathan Ullman, Testable and Actionable Calibration for Full Swap Regret
4	T 09/22	Multicalibration Materials: notes, slides Interesting Reading: Úrsula Hébert-Johnson, Michael P. Kim, Omer Reingold, and Guy N. Rothblum, Calibration for the (Computationally-Identifiable) Masses
5	F 09/25	Catch-Up Day Materials: notes, slides
6	T 09/29	Omniprediction Materials: notes, slides Interesting Reading: Parikshit Gopalan, Adam Tauman Kalai, Omer Reingold, Vatsal Sharan, and Udi Wieder, Omnipredictors Parikshit Gopalan, Lunjia Hu, Michael P. Kim, Omer Reingold, and Udi Wieder, Loss Minimization Through the Lens of Outcome Indistinguishability
7	F 10/02	Conformal Prediction Materials: notes, slides Interesting Reading: Glenn Shafer and Vladimir Vovk, A Tutorial on Conformal Prediction Osbert Bastani, Varun Gupta, Christopher Jung, Georgy Noarov, Ramya Ramalingam, and Aaron Roth, Practical Adversarial Multivalid Conformal Prediction
8	T 10/06	Overview of Robustness Materials: notes, slides
9	F 10/09	Robust Mean Estimation Materials: notes, slides Interesting Reading: Banghua Zhu, Jiantao Jiao, and Jacob Steinhardt, When does the Tukey median work?
10	T 10/13	Robustness in High Dimensions Materials: notes, slides Interesting Reading: Jacob Steinhardt, Moses Charikar, and Gregory Valiant, Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers
11	F 10/16	Efficient Robustness in High Dimensions Materials: notes, slides Interesting Reading: Ilias Diakonikolas, Gautam Kamath, Daniel Kane, Jerry Li, Ankur Moitra, and Alistair Stewart, Robust Estimators in High Dimensions without the Computational Intractability Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Jacob Steinhardt, and Alistair Stewart, SEVER: A Robust Meta-Algorithm for Stochastic Optimization
12	T 10/20	Distribution Shift and Calibration Materials: notes, slides Interesting Reading: Michael P. Kim, Christoph Kern, Shafi Goldwasser, Frauke Kreuter, and Omer Reingold, Universal Adaptability: Target-Independent Inference that Competes with Propensity Scoring
13	F 10/23	Training Data Memorization Materials: notes, slides Interesting Reading: Vitaly Feldman, Does Learning Require Memorization? A Short Tale about a Long Tail Nicholas Carlini, Florian Tramèr, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Úlfar Erlingsson, Alina Oprea, and Colin Raffel, Extracting Training Data from Large Language Models
14	T 10/27	Memorizing Irrelevant Training Data Materials: notes, slides Interesting Reading: Gavin Brown, Mark Bun, Vitaly Feldman, Adam Smith, and Kunal Talwar, When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning? Vitaly Feldman, Guy Kornowski, and Xin Lyu, Trade-offs in Data Memorization via Strong Data Processing Inequalities
15	F 10/30	Finish Memorization; Start Membership Inference Materials: notes, slides Interesting Reading: Nils Homer et al., Resolving Individuals Contributing Trace Amounts of DNA to Highly Complex Mixtures Using High-Density SNP Genotyping Microarrays Cynthia Dwork, Adam Smith, Thomas Steinke, and Jonathan Ullman, Exposed! A Survey of Attacks on Private Data Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov, Membership Inference Attacks against Machine Learning Models Samuel Yeom, Irene Giacomelli, Matt Fredrikson, and Somesh Jha, Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
16	T 11/03	Finish Membership Inference Materials: notes, slides Interesting Reading: Renaud Gaucher, Ephraim Linder, Adam Smith, Jonathan Ullman, and Lydia Zakynthinou, A Simple Presentation of Robust Membership Inference Attacks Cynthia Dwork, Adam Smith, Thomas Steinke, Jonathan Ullman, and Salil Vadhan, Robust Traceability from Trace Amounts
17	F 11/06	Defining Differential Privacy Materials: notes, slides Interesting Reading: Adam Smith and Jonathan Ullman, Privacy in Statistics and Machine Learning
18	T 11/10	Basic Differentially Private Algorithms Please fill out the poll for final class topics Materials: notes, slides Interesting Reading: Cynthia Dwork and Aaron Roth, The Algorithmic Foundations of Differential Privacy Salil Vadhan, The Complexity of Differential Privacy
19	F 11/13	The Gaussian Mechanism and Approximate Differential Privacy Materials: notes, slides Interesting Reading: Mark Bun and Thomas Steinke, Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds Ilya Mironov, Rényi Differential Privacy Jinshuo Dong, Aaron Roth, and Weijie J. Su, Gaussian Differential Privacy
20	T 11/17	Differentially Private (Stochastic) Gradient Descent Materials: notes, slides Interesting Reading: Raef Bassily, Adam Smith, and Abhradeep Thakurta, Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds Martín Abadi, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang, Deep Learning with Differential Privacy
21	F 11/20	Field trip to CRISP Instead of a normal class, we will attend Charles River Symposium on Privacy in 102 WVH. Please register so we order the right amount of food.
22	T 11/24	Catch-Up Day Please fill out the poll for project check-in slots Materials: slides
—	F 11/27	No Class: Thanksgiving Break
23	T 12/01	Students' Choice: TBD Materials: notes, slides
24	F 12/04	Students' Choice: TBD Materials: notes, slides
25	T 12/08	Students' Choice: TBD Materials: notes, slides
26	F 12/11	Project Presentations Please fill out the poll for final presentation slots
27	T 12/15	Project Presentations
28	F 12/18	Project Presentations