Zachary Lipton
@zacharylipton.bsky.social
Cofounder & CTO @ Abridge, Raj Reddy Associate Prof of ML @ CMU, occasional writer, relapsing 🎷, creator of d2l.ai & approximatelycorrect.com
We even found that sometimes with deep nets imputing 0 is better than running a fancy imputation algorithm because it’s more obvious which values are imputed so there’s less destruction of information.
April 23, 2025 at 8:29 AM
We even found that sometimes with deep nets imputing 0 is better than running a fancy imputation algorithm because it’s more obvious which values are imputed so there’s less destruction of information.
Yeah, it makes sense, it gives you all the info you have. A powerful enough model can learn any reasonable imputation strategy implicitly.
April 23, 2025 at 8:27 AM
Yeah, it makes sense, it gives you all the info you have. A powerful enough model can learn any reasonable imputation strategy implicitly.
Taking me back to 2016 baby. proceedings.mlr.press/v56/Lipton16...
In some clinical tasks the indicators are so useful, they’re almost as informative as the features themselves.
In some clinical tasks the indicators are so useful, they’re almost as informative as the features themselves.
proceedings.mlr.press
April 23, 2025 at 7:59 AM
Taking me back to 2016 baby. proceedings.mlr.press/v56/Lipton16...
In some clinical tasks the indicators are so useful, they’re almost as informative as the features themselves.
In some clinical tasks the indicators are so useful, they’re almost as informative as the features themselves.
Thus the “controversiality”. Point is, hard to imagine any non-political reason to get any other compact EV than a tesla. Seems like nobody is even close, which i found surprising given the growing market.
March 7, 2025 at 6:20 AM
Thus the “controversiality”. Point is, hard to imagine any non-political reason to get any other compact EV than a tesla. Seems like nobody is even close, which i found surprising given the growing market.
what sort of model was involved in the retrieval step?
February 16, 2025 at 11:30 PM
what sort of model was involved in the retrieval step?
...you’re thinking about infrastructure, user experience, orchestration, governance, and automation at scale. That’s a different game altogether."
February 7, 2025 at 8:24 PM
...you’re thinking about infrastructure, user experience, orchestration, governance, and automation at scale. That’s a different game altogether."
per ChatGPT:
"AI is no longer just “machine learning at scale.” It’s a full-stack engineering and economic transformation, where ML is just one piece of the puzzle. If you’re building modern AI systems, you’re thinking beyond ML—...
"AI is no longer just “machine learning at scale.” It’s a full-stack engineering and economic transformation, where ML is just one piece of the puzzle. If you’re building modern AI systems, you’re thinking beyond ML—...
February 7, 2025 at 8:24 PM
per ChatGPT:
"AI is no longer just “machine learning at scale.” It’s a full-stack engineering and economic transformation, where ML is just one piece of the puzzle. If you’re building modern AI systems, you’re thinking beyond ML—...
"AI is no longer just “machine learning at scale.” It’s a full-stack engineering and economic transformation, where ML is just one piece of the puzzle. If you’re building modern AI systems, you’re thinking beyond ML—...