14.5k citations
- SLAC National Accelerator LaboratoryUS5.1k papers
- Kavli Institute for Particle Astrophysics and CosmologyUS3.3k papers
- Centre National de la Recherche ScientifiqueFR2.2k papers
- University of California, BerkeleyUS2.2k papers
- California Institute of TechnologyUS2.1k papers
- Lawrence Berkeley National LaboratoryUS1.7k papers
- Massachusetts Institute of TechnologyUS1.7k papers
- Princeton UniversityUS1.5k papers
- The Ohio State UniversityUS1.5k papers
- University of California, Santa CruzUS1.5k papers
- University of Maryland, College ParkUS1.4k papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR1.4k papers
171 papers · 2 filters
Learning Personal Representations from fMRIby Predicting Neurofeedback Performance
Jhonathan Osin, Lior Wolf, Guy Gurevitch +5
We present a deep neural network method for learning a personal representation for individuals that are performing a self neuromodulation task, guided by functional MRI (fMRI). Thi…
Noether Networks: Meta-Learning Useful Conserved Quantities
Ferran Alet, Dylan Doblar, Allan Zhou +3
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often explo…
BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery
Chris Cundy, Aditya Grover, Stefano Ermon
A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic graph (DAG). Recent advances have enabled effecti…
On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
Xiaowu Dai, Yuhua Zhu
We study the statistical properties of the dynamic trajectory of stochastic gradient descent (SGD). We approximate the mini-batch SGD and the momentum SGD as stochastic differentia…
HyperSPNs: Compact and Expressive Probabilistic Circuits
Andy Shih, Dorsa Sadigh, Stefano Ermon
Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions. PCs are both ex…
NeuralProphet: Explainable Forecasting at Scale
Oskar Triebe, Hansika Hewamalage, Polina Pilyugina +3
We introduce NeuralProphet, a successor to Facebook Prophet, which set an industry standard for explainable, scalable, and user-friendly forecasting frameworks. With the proliferat…