Information-theoretic Foundations of Generative Adversarial Models: ...

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=wu3EsIHMHYE


Category:
Guide
Duration: 35:10
886 views
7

Lalitha Sankar (Arizona State University)
https://simons.berkeley.edu/talks/lalitha-sankar-arizona-state-university-2023-05-22
Information-Theoretic Methods for Trustworthy Machine Learning



Other Videos By Simons Institute for the Theory of Computing


2023-05-25Decision making with information-theoretic constraints
2023-05-25Information Thresholds in Structure Estimation
2023-05-25Fair, Explainable, and Lawful Machine Learning for High-Stakes Applications
2023-05-24KEYNOTE: Variational Formulations and Distributed Convex Optimization Methods for...
2023-05-24Improving Accuracy-Privacy Tradeoff via Model Reprogramming
2023-05-24Towards “One-Shot” Privacy Auditing and Estimation
2023-05-24The Saddle-Point Accountant for Differential Privacy
2023-05-24Contraction of Markov Kernels and Differential Privacy (PART II)
2023-05-24Contraction of Markov kernels and differential privacy (PART I)
2023-05-23KEYNOTE: Differential Privacy & Variants
2023-05-23Information-theoretic Foundations of Generative Adversarial Models: ...
2023-05-23Generalization bounds for Neural Network Based Decoders
2023-05-23Optimal Neural Network Compressors and the Manifold Hypothesis
2023-05-23Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values
2023-05-23Secure Distributed Matrix Multiplication
2023-05-23On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations
2023-05-23Majorizing Measures, Codes, and Information
2023-05-22KEYNOTE: A (Con)Sequential View of Information for Statistical Learning and Optimization
2023-05-06Black-Box Separations in Quantum Cryptography *Presented Virtually
2023-05-06Quantum pseudorandomness in Algorithmica, and its implications to cryptography and complexity
2023-05-06On the Computational Hardness Needed for Quantum Cryptography


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Information-Theoretic Methods for Trustworthy Machine Learning
Lalitha Sankar