Train-by-Reconnect: Decoupling Locations of Weights from their Values
- URL: http://arxiv.org/abs/2003.02570v6
- Date: Mon, 7 Dec 2020 06:26:35 GMT
- Title: Train-by-Reconnect: Decoupling Locations of Weights from their Values
- Authors: Yushi Qiu, Reiji Suda
- Abstract summary: We show that untrained deep neural networks (DNNs) are different from trained ones.
We propose a novel method named Lookahead Permutation (LaPerm) to train DNNs by reconnecting the weights.
When the initial weights share a single value, our method finds weight neural network with far better-than-chance accuracy.
- Score: 6.09170287691728
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: What makes untrained deep neural networks (DNNs) different from the trained
performant ones? By zooming into the weights in well-trained DNNs, we found it
is the location of weights that hold most of the information encoded by the
training. Motivated by this observation, we hypothesize that weights in
stochastic gradient-based method trained DNNs can be separated into two
dimensions: the locations of weights and their exact values. To assess our
hypothesis, we propose a novel method named Lookahead Permutation (LaPerm) to
train DNNs by reconnecting the weights. We empirically demonstrate the
versatility of LaPerm while producing extensive evidence to support our
hypothesis: when the initial weights are random and dense, our method
demonstrates speed and performance similar to or better than that of regular
optimizers, e.g., Adam; when the initial weights are random and sparse (many
zeros), our method changes the way neurons connect and reach accuracy
comparable to that of a well-trained fully initialized network; when the
initial weights share a single value, our method finds weight agnostic neural
network with far better-than-chance accuracy.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.