Randall Balestriero
3 papers in the PaperMetrix corpus
Papers by this author
-
Training Dynamics of Deep Network Linear Regions
2023 · arXiv (Cornell University)
The study of Deep Network (DN) training dynamics has largely focused on the evolution of the loss function, evaluated on or around train and test set data points. In fact, many DN phenomenon were first …
-
Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting
2025 · arXiv (Cornell University)
Catastrophic forgetting -- the phenomenon of a neural network learning a task t1 and losing the ability to perform it after being trained on some other task t2 -- is a long-standing problem for neural …
-
DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
2025 · arXiv (Cornell University)
Continued pretraining offers a promising solution for adapting foundation models to a new target domain. However, in specialized domains, available datasets are often very small, limiting the applicability of SSL methods developed for large-scale pretraining …