Birs- 24w5308: New Directions in Machine Learning Theory
-
Title: What governs predictive disparity in modern machine learning applications?
Speaker:
Link:
-
Title: Prediction-Powered Inference
Speaker:
Link:
-
Title: Bursting the Filter Bubble: Disincentivizing Echo Chambers in Social Networks
Speaker:
Link:
-
Title: A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
Speaker:
Link:
-
Title: Online matching with graph neural networks
Speaker:
Link:
-
Title: Step-by-Step Diffusion
Speaker:
Link:
-
Title: Dueling over dessert, mastering the art of repeated cake cutting
Speaker:
Link:
-
Title: Behavioral Economics-Inspired Multi-Agent Learning
Speaker:
Link:
-
Title: Theory of Multi-objective Machine Learning
Speaker:
Link:
-
Title: A multigroup perspective to go beyond loss minimization in ML
Speaker:
Link:
-
Title: Mechanisms of LLM Generalization: A Computational Approach
Speaker:
Link:
-
Title: Efficiently learning instance-optimal linear system solvers
Speaker:
Link:
-
Title: Should we predict in Latent Space in Self-Supervised Learning?
Speaker:
Link:
-
Title: Towards Theoretical Understanding of Extrapolation in Data Science
Speaker:
Link:
-
Title: Recent progress on interpretable clustering
Speaker:
Link:
-
Title: Fair Secretaries with Unfair Predictions
Speaker:
Link:
-
Title: Algorithmic tools for targeting sortition ideals
Speaker:
Link:
-
Title: Majority-of-Three: The Simplest Optimal Learner?
Speaker:
Link:
-
Title: Inherent Limitations for Characterizing Distribution Learning
Speaker:
Link:
-
Title: VC Theory vs. Empirical DP
Speaker:
Link: