most citedThe Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

1 citations · 1 across the 1 of their papers we have counts for

collaborators

2 papers

cs.LG2025★ 1 cited

The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

Devin Kwok, Gül Sena Altıntaş, Colin Raffel +1

Neural network training is inherently sensitive to initialization and the randomness induced by stochastic gradient descent. However, it is unclear to what extent such effects lead…

cs.LG2023

Disentangling Linear Mode-Connectivity

Gul Sena Altintas, Gregor Bachmann, Lorenzo Noci +1

Linear mode-connectivity (LMC) (or lack thereof) is one of the intriguing characteristics of neural network loss landscapes. While empirically well established, it unfortunately st…