I have been looking at the draft for a while, I am surprised you had a hard time publishing it, it is a super cool work! Will it be included in the TorchDR package ?
June 27, 2025 at 10:17 AM
I have been looking at the draft for a while, I am surprised you had a hard time publishing it, it is a super cool work! Will it be included in the TorchDR package ?
TL;DR:
✅ Theoretical guarantees for nonlinear meta-learning
✅ Explains when and how aggregation helps
✅ Connects RKHS regression, subspace estimation & meta-learning
Co-led with Zhu Li 🙌, with invaluable support from @arthurgretton.bsky.social, Samory Kpotufe.
✅ Theoretical guarantees for nonlinear meta-learning
✅ Explains when and how aggregation helps
✅ Connects RKHS regression, subspace estimation & meta-learning
Co-led with Zhu Li 🙌, with invaluable support from @arthurgretton.bsky.social, Samory Kpotufe.
May 26, 2025 at 4:50 PM
TL;DR:
✅ Theoretical guarantees for nonlinear meta-learning
✅ Explains when and how aggregation helps
✅ Connects RKHS regression, subspace estimation & meta-learning
Co-led with Zhu Li 🙌, with invaluable support from @arthurgretton.bsky.social, Samory Kpotufe.
✅ Theoretical guarantees for nonlinear meta-learning
✅ Explains when and how aggregation helps
✅ Connects RKHS regression, subspace estimation & meta-learning
Co-led with Zhu Li 🙌, with invaluable support from @arthurgretton.bsky.social, Samory Kpotufe.
Even with nonlinear representation you can estimate the shared structure at a rate improving in both N (tasks) and n (samples per task). This leads to parametric rates on the target task!⚡
Bonus: for linear kernels, our results recover known linear meta-learning rates.
Bonus: for linear kernels, our results recover known linear meta-learning rates.
May 26, 2025 at 4:50 PM
Even with nonlinear representation you can estimate the shared structure at a rate improving in both N (tasks) and n (samples per task). This leads to parametric rates on the target task!⚡
Bonus: for linear kernels, our results recover known linear meta-learning rates.
Bonus: for linear kernels, our results recover known linear meta-learning rates.
Short answer: Yes ✅
Key idea💡: Instead of learning each task well, under-regularise per-task estimators to better estimate the shared subspace in the RKHS.
Even though each task is noisy, their span reveals the structure we care about.
Bias-variance tradeoff in action.
Key idea💡: Instead of learning each task well, under-regularise per-task estimators to better estimate the shared subspace in the RKHS.
Even though each task is noisy, their span reveals the structure we care about.
Bias-variance tradeoff in action.
May 26, 2025 at 4:50 PM
Short answer: Yes ✅
Key idea💡: Instead of learning each task well, under-regularise per-task estimators to better estimate the shared subspace in the RKHS.
Even though each task is noisy, their span reveals the structure we care about.
Bias-variance tradeoff in action.
Key idea💡: Instead of learning each task well, under-regularise per-task estimators to better estimate the shared subspace in the RKHS.
Even though each task is noisy, their span reveals the structure we care about.
Bias-variance tradeoff in action.
Our paper analyses a meta-learning setting where tasks share a finite dimensional subspace of a Reproducing Kernel Hilbert Space.
Can we still estimate this shared representation efficiently — and learn new tasks fast?
Can we still estimate this shared representation efficiently — and learn new tasks fast?
May 26, 2025 at 4:50 PM
Our paper analyses a meta-learning setting where tasks share a finite dimensional subspace of a Reproducing Kernel Hilbert Space.
Can we still estimate this shared representation efficiently — and learn new tasks fast?
Can we still estimate this shared representation efficiently — and learn new tasks fast?
Most prior theory assumes linear structure: All tasks share a linear representation, and task-specific parts are also linear.
Then: we can show improved learning rates as the number of tasks increases.
But reality is nonlinear. What then?
Then: we can show improved learning rates as the number of tasks increases.
But reality is nonlinear. What then?
May 26, 2025 at 4:50 PM
Most prior theory assumes linear structure: All tasks share a linear representation, and task-specific parts are also linear.
Then: we can show improved learning rates as the number of tasks increases.
But reality is nonlinear. What then?
Then: we can show improved learning rates as the number of tasks increases.
But reality is nonlinear. What then?
Meta-learning = using many related tasks to help learn new ones faster.
In practice (e.g. with neural nets), this usually means learning a shared representation across tasks — so we can train quickly on unseen ones.
But: what’s the theory behind this? 🤔
In practice (e.g. with neural nets), this usually means learning a shared representation across tasks — so we can train quickly on unseen ones.
But: what’s the theory behind this? 🤔
May 26, 2025 at 4:50 PM
Meta-learning = using many related tasks to help learn new ones faster.
In practice (e.g. with neural nets), this usually means learning a shared representation across tasks — so we can train quickly on unseen ones.
But: what’s the theory behind this? 🤔
In practice (e.g. with neural nets), this usually means learning a shared representation across tasks — so we can train quickly on unseen ones.
But: what’s the theory behind this? 🤔
Reposted by Dimitri Meunier
Link to the video: youtu.be/nLGBTMfTvr8?...
Interview of Statistics and ML Expert - Pierre Alquier
YouTube video by ML New Papers
youtu.be
April 28, 2025 at 11:01 AM
Link to the video: youtu.be/nLGBTMfTvr8?...