Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Knutins, Maksis"'
Autor:
Fetterman, Abraham J., Kitanidis, Ellie, Albrecht, Joshua, Polizzi, Zachary, Fogelman, Bryden, Knutins, Maksis, Wróblewski, Bartosz, Simon, James B., Qiu, Kanjun
Hyperparameter tuning of deep learning models can lead to order-of-magnitude performance gains for the same amount of compute. Despite this, systematic tuning is uncommon, particularly for large models, which are expensive to evaluate and tend to hav
Externí odkaz:
http://arxiv.org/abs/2306.08055
Autor:
Simon, James B., Knutins, Maksis, Ziyin, Liu, Geisz, Daniel, Fetterman, Abraham J., Albrecht, Joshua
We present a simple picture of the training process of joint embedding self-supervised learning methods. We find that these methods learn their high-dimensional embeddings one dimension at a time in a sequence of discrete, well-separated steps. We ar
Externí odkaz:
http://arxiv.org/abs/2303.15438
Autor:
Albrecht, Joshua, Fetterman, Abraham J., Fogelman, Bryden, Kitanidis, Ellie, Wróblewski, Bartosz, Seo, Nicole, Rosenthal, Michael, Knutins, Maksis, Polizzi, Zachary, Simon, James B., Qiu, Kanjun
Despite impressive successes, deep reinforcement learning (RL) systems still fall short of human performance on generalization to new tasks and environments that differ from their training. As a benchmark tailored for studying RL generalization, we i
Externí odkaz:
http://arxiv.org/abs/2210.13417
Adaptive traffic signal control is one key avenue for mitigating the growing consequences of traffic congestion. Incumbent solutions such as SCOOT and SCATS require regular and time-consuming calibration, can't optimise well for multiple road use mod
Externí odkaz:
http://arxiv.org/abs/2008.11634