no code implementations • 5 Feb 2024 • Yu-Guan Hsieh, James Thornton, Eugene Ndiaye, Michal Klein, Marco Cuturi, Pierre Ablin
Beyond minimizing a single training loss, many deep learning estimation pipelines rely on an auxiliary objective to quantify and encourage desirable properties of the model (e. g. performance on another dataset, robustness, agreement with a prior).
2 code implementations • 16 Jan 2024 • Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar, Joshua M Susskind, Armand Joulin
Specifically, we highlight two key findings: (1) the performance of the visual features scale with both the model capacity and the quantity of data, (2) the value of the objective function correlates with the performance of the model on downstream tasks.
Ranked #333 on Image Classification on ImageNet (using extra training data)
no code implementations • 24 Jul 2023 • Sören Becker, Michal Klein, Alexander Neitz, Giambattista Parascandolo, Niki Kilbertus
We develop a transformer-based sequence-to-sequence model that recovers scalar ordinary differential equations (ODEs) in symbolic form from irregularly sampled and noisy observations of a single solution trajectory.
no code implementations • 20 Jun 2023 • Michal Klein, Aram-Alexandre Pooladian, Pierre Ablin, Eugène Ndiaye, Jonathan Niles-Weed, Marco Cuturi
Because of such difficulties, existing approaches rarely depart from the default choice of estimating such maps with the simple squared-Euclidean distance as the ground cost, $c(x, y)=\|x-y\|^2_2$.
no code implementations • 8 Feb 2023 • Marco Cuturi, Michal Klein, Pierre Ablin
Optimal transport (OT) theory focuses, among all maps $T:\mathbb{R}^d\rightarrow \mathbb{R}^d$ that can morph a probability measure onto another, on those that are the ``thriftiest'', i. e. such that the averaged cost $c(x, T(x))$ between $x$ and its image $T(x)$ be as small as possible.
no code implementations • 5 Nov 2022 • Sören Becker, Michal Klein, Alexander Neitz, Giambattista Parascandolo, Niki Kilbertus
Natural laws are often described through differential equations yet finding a differential equation that describes the governing law underlying observed data is a challenging and still mostly manual task.