Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains or the Whole Domain

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=7raKN7zofno


Duration: 0:00
180 views
0

Tengyu Ma (Stanford University)
https://simons.berkeley.edu/talks/tengyu-ma-stanford-university-2024-11-14
Domain Adaptation and Related Areas



Other Videos By Simons Institute for the Theory of Computing


2024-11-18Omnipredicting Single-Index Models with Multi-Index Models
2024-11-17The Truth About Your Lying Calibrated Forecaster: How to Design Truthful Calibration Measures
2024-11-17A Discrepancy-Based Theory of Adaptation
2024-11-17Bypassing the Impossibility of Online Learning Thresholds: Unbounded Losses and Transductive Priors
2024-11-17Learning from Dynamics
2024-11-14Scalably Understanding AI with AI
2024-11-14Domain Adaptation-- 20 years of theory chasing practice
2024-11-14Adaptive Data Collection via Autoregressive Generation
2024-11-14Panel Discussion
2024-11-14Open-Source and Science in the Era of Foundation Models
2024-11-13Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains or the Whole Domain
2024-11-12Distribution shift in ecological data: generalization vs. specialization,
2024-11-12Transfer learning via local convergence rates of the nonparametric least squares estimator
2024-11-12Transfer learning for weak-to-strong generalization
2024-11-12User-level and federated local differential privacy
2024-11-11The Evolution of Domain Transfer in the Era of Pre-trained Language Models
2024-11-11Label Noise: Ignorance is Bliss
2024-11-11The Data Addition Dilemma
2024-11-11Pseudo-Labeling for Covariate Shift Adaptation
2024-11-11How Transformers Learn Causal Structure with Gradient Descent
2024-10-16The Enigma of LLMs: on Creativity, Compositionality, Pluralism, and Paradoxes