Newsroom
statistical inference
-
S&DS Seminar: Adam Block (Columbia), “Scaling Inference-Time Compute: From Self-Improvement to Pessimism”
Abstract: Language models increasingly rely on scaling inference-time computation to achieve state-of-the-art performance on a growing number of reasoning tasks. A popular paradigm for such computational scaling is Best-of-N (BoN) sampling, where a model generates multiple candidate responses to a given question and selects the one among them as the most likely to be correct.…
-
S&DS Seminar: Jingfeng Wu (Berkeley), “Gradient Descent Dominates Ridge: A Statistical View on Implicit Regularization”
Talk summary: A key puzzle in deep learning is how simple gradient methods find generalizable solutions without explicit regularization. This talk discusses the implicit regularization of gradient descent (GD) through the lens of statistical dominance. Using least squares as a clean proxy, we present two surprising findings. First, GD dominates ridge regression. For any well-specified…
-
FDS Colloquium: Houman Owhadi (Caltech), “Co-discovering graphical structure and functional relationships within data: A Gaussian Process framework for connecting the dots”
Abstract: Most scientific challenges can be framed into one of the following three levels of complexity of function approximation. Examples of Type 2 problems include solving and learning (possibly stochastic) nonlinear partial differential equations (PDEs), while Type 3 problems encompass learning dependencies between variables in a mechanical system, identifying chemical reaction networks, and determining relationships between…
-
Workshop Honoring Andrew Barron: Forty Years at the Interplay of Information Theory, Probability and Statistical Learning (Day 3)
The Workshop Honoring Andrew Barron: “Forty Years at the Interplay of Information Theory, Probability and Statistical Learning” will take place from Friday, April 26 to Sunday, April 28, 2024, at Yale University in New Haven, CT. Click for the main event page & registration Events include:
-
Workshop Honoring Andrew Barron: Forty Years at the Interplay of Information Theory, Probability and Statistical Learning (Day 2)
The Workshop Honoring Andrew Barron: “Forty Years at the Interplay of Information Theory, Probability and Statistical Learning” will take place from Friday, April 26 to Sunday, April 28, 2024, at Yale University in New Haven, CT. Click for the main event page & registration Events include:
-
Workshop Honoring Andrew Barron: Forty Years at the Interplay of Information Theory, Probability and Statistical Learning
The Workshop Honoring Andrew Barron: “Forty Years at the Interplay of Information Theory, Probability and Statistical Learning” will take place from Friday, April 26 to Sunday, April 28, 2024, at Yale University in New Haven, CT. Link to the main event page Events include: