Jascha Sohl‐Dickstein

12.4k citations
60 papers · 2.2k indexed · 1 hit paper · h-index 23

Impact in

Papers in

    • Neural Networks and Applications 15
    • Machine Learning and Data Classification 8
    • Stochastic Gradient Optimization Techniques 7
    • Adversarial Robustness in Machine Learning 7
    • Gaussian Processes and Bayesian Inference 7
    • Generative Adversarial Networks and Image Synthesis 8
    • Advanced Neural Network Applications 7

Jascha Sohl‐Dickstein

57 papers receiving 2.1k citations

Hit Papers

Deep Knowledge Tracing 2015 · 365 citations
3652015202620182022100200300

Peers

Jascha Sohl‐Dickstein
Comparison fields: 5 of 153
  • Computer Science Applications 247
  • Astronomy and Astrophysics 620
  • Artificial Intelligence 1.0k
  • Computer Vision and Pattern Recognition 375
  • Computational Mathematics 8
Replace Fernando Pérez with:
Fernando Pérez Spain
Steven Reece United Kingdom
Michael C. Burl United States
John Williamson United Kingdom
Jos B. T. M. Roerdink Netherlands
William P. Thurston United States
Anne Trefethen United Kingdom
Steve Bryson United States
Lior Shamir United States
Peter Sadowski United States
Jascha Sohl‐Dickstein relative to Fernando Pérez Spain Fernando Pérez's profile →
Citations per field
00.5×3.8×
Fernando Pérez · 1×
Citations per year

Countries citing papers authored by Jascha Sohl‐Dickstein

Since Specialization
Citations

This map shows the geographic impact of Jascha Sohl‐Dickstein's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Jascha Sohl‐Dickstein with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Jascha Sohl‐Dickstein more than expected).

Fields of papers citing papers by Jascha Sohl‐Dickstein

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Jascha Sohl‐Dickstein. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Jascha Sohl‐Dickstein. The network helps show where Jascha Sohl‐Dickstein may publish in the future.

Co-authors

The 25 scholars most cited alongside Jascha Sohl‐Dickstein, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Jascha Sohl‐Dickstein Line = papers co-authored together Jascha Sohl‐Dickstein links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown
#Work
1
Score-Based Generative Modeling through Stochastic Differential Equations
20216
2
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
20203
3
Finite Versus Infinite Neural Networks: an Empirical Study
20205
4
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
20209
5
A Mean Field Theory of Batch Normalization
201913
6
Meta-Learning Update Rules for Unsupervised Representation Learning
20184
7
Sensitivity and Generalization in Neural Networks: an Empirical Study
201818
8
Learning Unsupervised Learning Rules
20189
9
Deep Neural Networks as Gaussian Processes
201876
10
Learned optimizers that outperform SGD on wall-clock and validation loss
20183
11
Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes.
20185
12
Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
20176
13
Explaining the Learning Dynamics of Direct Feedback Alignment
20173
14
Exponential expressivity in deep neural networks through transient chaos
201636
15
Measurably Increasing Motivation in MOOCs.
20135
16
An adaptive low dimensional quasi-Newton sum of functions optimizer.
20133
17
Minimum Probability Flow Learning
201115
18
A Martian Year of High Resolution Multispectral Imaging from the Pancam Instruments on the Mars Exploration Rovers Spirit and Opportunity
20060
19
Modeling Visible/Near-Infrared Photometric Properties of Dustfall on a Known Substrate
200516
20
The Single Scattering Albedo of Martian Atmospheric Dust in the 290-500 nm Region
20021

About Jascha Sohl‐Dickstein

Jascha Sohl‐Dickstein is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Health Informatics and Computer Graphics and Computer-Aided Design, having authored 60 papers that have together received 2.2k indexed citations. Recurring topics across this work include Neural Networks and Applications (15 papers), Planetary Science and Exploration (9 papers), Machine Learning and Data Classification (8 papers), Generative Adversarial Networks and Image Synthesis (8 papers), Stochastic Gradient Optimization Techniques (7 papers), Adversarial Robustness in Machine Learning (7 papers), Advanced Neural Network Applications (7 papers) and Gaussian Processes and Bayesian Inference (7 papers). The work is most often cited by research in Computer Science Applications (247 citations), Astronomy and Astrophysics (620 citations), Artificial Intelligence (1.0k citations), Computer Vision and Pattern Recognition (375 citations) and Computational Mathematics (8 citations). Jascha Sohl‐Dickstein has collaborated with scholars based in United States, United Kingdom and Canada. Frequent co-authors include Surya Ganguli, Ben Poole, Luke Metz, Chris Piech, Jonathan Huang, Leonidas Guibas, Mehran Sahami, Jeffrey Pennington, Yasaman Bahri and David Pfau. Their work appears in journals such as Journal of Geophysical Research Atmospheres, Medical Physics, Journal of Vision, Nature Communications and Physical Review Letters.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026