Ask a question below.
Published answers will appear here.
Compression is key to intelligence. We introduce requential coding, pushing compression to the limit. We show larger models and ensembles are much stronger compressors, better than even 1 bit per parameter, with better generalization bounds. I'm so excited about this work! https://twitter.com/ShikaiQiu/status/2077040591666290703
I'm so excited about this new work. We introduce requential coding, pushing compression to the absolute limits! We show larger neural networks and ensembles are much stronger compressors, even in an absolute sense, with better generalization bounds. https://twitter.com/ShikaiQiu/status/2077040591666290703
Compression is key to intelligence. We introduce requential coding, pushing compression to the limit. We show larger models and ensembles are much stronger compressors, better than even 1 bit per parameter, with better generalization bounds. I'm so excited about this work! https://twitter.com/ShikaiQiu/status/2077040591666290703
I'm so excited about this new work. We introduce requential coding, pushing compression to the absolute limits! We show larger neural networks and ensembles are much stronger compressors, even in an absolute sense, with better generalization bounds. https://twitter.com/ShikaiQiu/status/2077040591666290703
Ask a question below.
Published answers will appear here.