no code implementations • 2 Mar 2024 • Akshit Goyal, Jason W. Rocks, Pankaj Mehta
How ecosystems respond to environmental perturbations is a fundamental question in ecology, made especially challenging due to the strong coupling between species and their environment.
1 code implementation • 24 Mar 2023 • Rylan Schaeffer, Mikail Khona, Zachary Robertson, Akhilan Boopathy, Kateryna Pistunova, Jason W. Rocks, Ila Rani Fiete, Oluwasanmi Koyejo
Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterized (data undersampled) regime.
no code implementations • 6 Mar 2023 • Zhijie Feng, Robert Marsland III, Jason W. Rocks, Pankaj Mehta
Ecosystems are commonly organized into trophic levels -- organisms that occupy the same level in a food chain (e. g., plants, herbivores, carnivores).
no code implementations • 10 Mar 2022 • Jason W. Rocks, Pankaj Mehta
We show that the linear random features model exhibits three phase transitions: two different transitions to an interpolation regime where the training error is zero, along with an additional transition between regimes with large bias and minimal bias.
no code implementations • 25 Mar 2021 • Jason W. Rocks, Pankaj Mehta
Classical regression has a simple geometric description in terms of a projection of the training labels onto the column space of the design matrix.
no code implementations • 26 Oct 2020 • Jason W. Rocks, Pankaj Mehta
In both models, increasing the number of fit parameters leads to a phase transition where the training error goes to zero and the test error diverges as a result of the variance (while the bias remains finite).