Quynh Nguyen, Marco Mondelli, Pierre Bréchet
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The question of how and why the phenomenon of mode connectivity occurs in training deep neural networks has gained remarkable attention in the research community. From a theoretical perspective, two possible explanations have been proposed: (i) the loss function has connected sublevel sets, and (ii) the solutions found by stochastic gradient descent are dropout stable. While these explanations provide insights into the phenomenon, their assumptions are not always satisfied in practice. In particular, the first approach requires the network to have one layer with order of N neurons (N being the number of training samples), while the second one requires the loss to be almost invariant after removing half of the neurons at each layer (up to some rescaling of the remaining ones). In this work, we improve both conditions by exploiting the quality of the features at every intermediate layer together with a milder over-parameterization requirement. More specifically, we show that: (i) under generic assumptions on the features of intermediate layers, it suffices that the last two hidden layers have order of N neurons, and (ii) if subsets of features at each layer are linearly separable, then almost no overparameterization is needed to show the connectivity. Our experiments confirm that the proposed condition ensures the connectivity of solutions found by stochastic gradient descent, even in settings where the previous requirements do not hold. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2102.09671")
get_code_for_paper("2102.09671")
have("2102.09671")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2102.09671.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2102.09671)
Connect an agent — have() is free.