collaborators

5 papers

cs.LG2025

An Effective Gram Matrix Characterizes Generalization in Deep Networks

Rubing Yang, Pratik Chaudhari

We derive a differential equation that governs the evolution of the generalization gap when a deep network is trained by gradient descent. This differential equation is controlled…

cs.CV2025

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations

Anthony Bisulco, Rahul Ramesh, Randall Balestriero +1

Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning…

cs.LG2025

Prospective Learning in Retrospect

Yuxin Bai, Cecelia Shuai, Ashwin De Silva +3

In most real-world applications of artificial intelligence, the distributions of the data and the goals of the learners tend to change over time. The Probably Approximately Correct…

cs.CV2025

Many Perception Tasks are Highly Redundant Functions of their Input Data

Rahul Ramesh, Anthony Bisulco, Ronald W. DiTullio +4

We show that many perception tasks, from visual recognition, semantic segmentation, optical flow, depth estimation to vocalization discrimination, are highly redundant functions of…

stat.ML2025

Prospective Learning: Learning for a Dynamic Future

Ashwin De Silva, Rahul Ramesh, Rubing Yang +3

In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably appro…