Search Results for author:
Found 6 papers, 1 papers with code
Careful with that Scalpel: Improving Gradient Surgery with an EMA
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).
Scalable Pre-training of Large Autoregressive Image Models
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)
Predicting Ordinary Differential Equations with Transformers
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.
Learning Costs for Structured Monge Displacements
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, $c(x, y)=\|x-y\|^2_2$.
Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps
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.
Discovering ordinary differential equations that govern time-series
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.
