Andrew Gordon Wilson
@andrewgwils
Machine Learning Professor
ID:2800204849
https://cims.nyu.edu/~andrewgw 09-09-2014 16:14:15
2,0K Tweets
26,5K Followers
717 Following
Thanks a lot Cohere For AI for the invitation. I had a great time presenting our work on generalization bounds for LLMs and the questions were insightful.
The process of preparing a talk can be very rewarding 🥳 Thanks Micah Goldblum for helping me craft the story of this talk.
Are all these time-series-specific model design necessary for deep forecasters / foundation forecasting models? In Chronos, we claim no novelty in time series modeling, but that's exactly the point. 'Everything should be made as simple as possible, but no simpler.' #TimeSeries
🚀 Excited to share that we released Chronos today. Chronos is a framework for building pretrained time series models based on language model architectures.
Simple idea: quantize time series into tokens and feed them into 🤗 Hugging Face models.
🧵
Great work, great Team: today we released Chronos, a family of pretrained, LLM-based time series models. Simple core idea: quantize series to get tokens, feed it into 🤗 Hugging Face models, done.
📝 arxiv.org/abs/2403.07815
💻 github.com/amazon-science…
🤗 huggingface.co/amazon/chronos…
Do LLMs simply memorize and parrot their pretraining data or do they learn patterns that generalize? Let’s put this to the test! We compute the first generalization guarantees for LLMs.
w/ Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner, Andrew Gordon Wilson
arxiv.org/abs/2312.17173
1/9
In this work we construct the first nonvacuous generalization bounds for LLMs, helping to explain why these models generalize.
w/ Sanae Lotfi, Yilun Kuang, Tim G. J. Rudner Micah Goldblum, Andrew Gordon Wilson
arxiv.org/abs/2312.17173
A 🧵on how we make these bounds
1/9
I'm glad to see losslandscape.com is still going strong. Javier Ideami has beautiful visualizations. The geometric properties of neural network training objectives, such as mode connectivity, make deep learning truly distinct.