Pierre Ablin (@PierreAblin) / X

Pierre Ablin

899 posts

Pierre Ablin

@PierreAblin

pierreablin.bsky.social Machine learning research @Apple

Paris, France

Joined July 2018

Pinned
Pierre Ablin
@PierreAblin
Sep 7, 2024
70 lines of code to massively accelerate LLM training! arxiv.org/abs/2409.03137
91K
Pierre Ablin
@PierreAblin
Jan 3, 2024
What better way to start the year than with a whiteboard with a view ?
179K
Pierre Ablin
@PierreAblin
Aug 15, 2021
Imitation is the sincerest form of flattery 🙌🙌🙌 arxiv.org/abs/2102.07870 arxiv.org/abs/2108.05862
Pierre Ablin
@PierreAblin
Sep 21, 2023
🍏🍏🍏 Apple ML Research in Paris has multiple open research internship positions! 🍎🍎🍎 We are looking for Ph.D. students interested in generative modeling, optimization or uncertainty quantification, with applications to challenging scientific problems. Details below 👇👇👇
178K
Pierre Ablin
@PierreAblin
Oct 6, 2020
Roger Penrose just won a Nobel prize in physics for black holes theory ! He is also famous for the Moore-Penrose inverse, which extends the notion of matrix inverse to rectangular and singular matrices. en.m.wikipedia.org/wiki/Moore%E2%…
Pierre Ablin
@PierreAblin
Oct 4, 2024
🍏 Apple ML research in Paris has multiple open internship positions!🍎 We are looking for Ph.D. students interested in generative modeling, optimization, large-scale learning or uncertainty quantification, with applications to challenging scientific problems. Details below 👇
107K
Pierre Ablin
@PierreAblin
May 10, 2021
New paper out : Momentum Residual Neural Networks ! Introducing a new drop-in replacement for any ResNet that makes it invertible, thus saving loads of memory ! With @m_e_sander @mblondel_ml & @gabrielpeyre Preprint : arxiv.org/abs/2102.07870 Accepted at ICML 🍾🍾🍾 1/6
Pierre Ablin
@PierreAblin
Sep 8, 2022
Apple ML Research in Paris has open research internship positions ! Looking for PhD students with background in ML / optimization. Internships are onsite, should happen anytime from now until sep. 2023. Please DM me if interested :)
Pierre Ablin
@PierreAblin
Jan 5, 2022
An important intuition about Stochastic Gradient Descent (SGD) is that when you are far from the solutions, individual stochastic gradients will more or less point in the same direction, but at optimum, since their average is 0, they will all point in different directions !
GIF
Pierre Ablin
@PierreAblin
Jul 3, 2023
New paper out : a simple way to have optimal transport with sparse displacements🎆 "Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps" arxiv.org/abs/2302.04065 w. @CuturiMarco and Michal Klein A small thread👇
GIF
41K
Pierre Ablin
@PierreAblin
Sep 7, 2021
Here are the first 100 principal components of the Imagenet dataset ! I had never seen this before, so I thought I'd give it a try :) Nothing too surprising, it looks like the principal components of most natural image datasets.
Pierre Ablin
@PierreAblin
Dec 18, 2024
🍏🍏🍏 Come work with us at Apple Machine Learning Research! 🍏🍏🍏 Our team focuses on curiosity-based, open research. We work on several topics, including LLMs, optimization, optimal transport, uncertainty quantification, and generative modeling. Infos 👇
48K
Pierre Ablin
@PierreAblin
Mar 18, 2019
Illustration of the Lasso and its path in 2D: for t small enough, the solution is sparse!
GIF
Pierre Ablin
@PierreAblin
Jul 11, 2023
TIL you can see double descent when fitting 1d polynomials: - When degree < # samples: low variance, high bias - when degree ~ # samples: super high variance - when degree >> # samples: low norm solution, you get interpolation + extrapolation ! Nice ref: arxiv.org/abs/1903.09139
GIF
47K