Neural Networks And Spurious Correlations
Aditi Raghunathan (UC Berkeley)
https://simons.berkeley.edu/talks/neural-networks-and-spurious-correlations
Algorithmic Aspects of Causal Inference
Neural networks trained on large datasets have powered several notable successes across various domains. However, such models often fail in the presence of distribution shifts because they can pick up on spurious correlations present in the dataset. In this talk, I will discuss how to train neural networks that are robust to known spurious correlations. We will see that this leads to counter-intuitive observations about the effect of model size and training data. Finally, I will discuss some approaches to mitigating the effect of spurious correlations in the absence of complete information about the spurious correlations.
Видео Neural Networks And Spurious Correlations канала Simons Institute
https://simons.berkeley.edu/talks/neural-networks-and-spurious-correlations
Algorithmic Aspects of Causal Inference
Neural networks trained on large datasets have powered several notable successes across various domains. However, such models often fail in the presence of distribution shifts because they can pick up on spurious correlations present in the dataset. In this talk, I will discuss how to train neural networks that are robust to known spurious correlations. We will see that this leads to counter-intuitive observations about the effect of model size and training data. Finally, I will discuss some approaches to mitigating the effect of spurious correlations in the absence of complete information about the spurious correlations.
Видео Neural Networks And Spurious Correlations канала Simons Institute
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Berkeley in the 80s, Episode 5: Richard Karp
Adversarial Examples in Deep Learning
Probabilistic Programming for Augmented Intelligence
Quantum Advantage Without Structure
Recent Advances in Quantum Simulation with Applications to Chemistry and Field Theory
Remarks on the Discrete Cube
Fast Reinforcement Learning With Generalized Policy Updates
"The Problem with Qubits"
Stability and Learning in Repeated Games
Machine Learning-based Design of Proteins and Small Molecules
Exact Asymptotics and Universality for Gradient Flows and Empirical Risk Minimizers
Recent Developments in Supervised Learning With Noise
Rates of Normal Approximation for Typical Weighted Sums
Planning and Markov Decision Processes Part 1 (reupload)
Reductionism in Reinforcement Learning
Submodular Optimization
Tractable Learning in Structured Probability Spaces
Using Molecular Networks to Seed Predictive Hierarchies of Cell Systems
Panel | Quantum Colloquium
Tractable Probabilistic Circuits
Algorithmic Fairness From The Lens Of Causality And Information Theory