pith. sign in

Jascha Sohl-Dickstein

Identifiers

  • name variant Jascha Sohl-Dickstein 0.60 · backfill

Papers (48)

  1. AI Organizations are More Effective but Less Aligned than Individual Agents cs.AI · 2026 · author #8
  2. The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity? cs.AI · 2026 · author #5
  3. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models cs.CL · 2022 · author #182
  4. Score-Based Generative Modeling through Stochastic Differential Equations cs.LG · 2020 · author #2
  5. Using learned optimizers to make models robust to input noise cs.LG · 2019 · author #4
  6. The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study cs.LG · 2019 · author #2
  7. A Mean Field Theory of Batch Normalization cs.NE · 2019 · author #4
  8. Eliminating all bad Local Minima from Loss Landscapes without even adding an Extra Unit stat.ML · 2019 · author #1
  9. Measuring the Effects of Data Parallelism on Neural Network Training cs.LG · 2018 · author #4
  10. Understanding and correcting pathologies in the training of learned optimizers cs.NE · 2018 · author #5
  11. Guided evolutionary strategies: Augmenting random search with surrogate gradients cs.NE · 2018 · author #5
  12. Stochastic natural gradient descent draws posterior samples in function space cs.LG · 2018 · author #5
  13. PCA of high dimensional random walks with comparison to neural network training stat.ML · 2018 · author #2
  14. Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks stat.ML · 2018 · author #3
  15. Meta-Learning Update Rules for Unsupervised Representation Learning cs.LG · 2018 · author #4
  16. Sensitivity and Generalization in Neural Networks: an Empirical Study stat.ML · 2018 · author #5
  17. Generalizing Hamiltonian Monte Carlo with Neural Networks stat.ML · 2017 · author #3
  18. Deep Neural Networks as Gaussian Processes stat.ML · 2017 · author #6
  19. A Correspondence Between Random Neural Networks and Statistical Field Theory stat.ML · 2017 · author #3
  20. SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability stat.ML · 2017 · author #4
  21. REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models cs.LG · 2017 · author #5
  22. Learned Optimizers that Scale and Generalize cs.LG · 2017 · author #7
  23. Improved generator objectives for GANs cs.LG · 2016 · author #3
  24. Capacity and Trainability in Recurrent Neural Networks stat.ML · 2016 · author #2
  25. Input Switched Affine Networks: An RNN Architecture Designed for Interpretability cs.AI · 2016 · author #4
  26. Survey of Expressivity in Deep Neural Networks stat.ML · 2016 · author #5
  27. Unrolled Generative Adversarial Networks cs.LG · 2016 · author #4
  28. Deep Information Propagation stat.ML · 2016 · author #4
  29. Exponential expressivity in deep neural networks through transient chaos stat.ML · 2016 · author #4
  30. On the Expressive Power of Deep Neural Networks stat.ML · 2016 · author #5
  31. Density estimation using Real NVP cs.LG · 2016 · author #2
  32. A universal tradeoff between power, precision and speed in physical communication cond-mat.stat-mech · 2016 · author #2
  33. A Markov Jump Process for More Efficient Hamiltonian Monte Carlo stat.ML · 2015 · author #4
  34. Deep Knowledge Tracing cs.AI · 2015 · author #7
  35. Note on Equivalence Between Recurrent Neural Network Time Series Models and Variational Bayesian Models cs.LG · 2015 · author #1
  36. Deep Unsupervised Learning using Nonequilibrium Thermodynamics cs.LG · 2015 · author #1
  37. Hamiltonian Monte Carlo Without Detailed Balance stat.CO · 2014 · author #1
  38. Analyzing noise in autoencoders and deep networks cs.NE · 2014 · author #2
  39. Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods cs.LG · 2013 · author #1
  40. Higher Order Correlations within Cortical Layers Dominate Functional Connectivity in Microcolumns q-bio.NC · 2013 · author #2
  41. Minimum and maximum entropy distributions for binary systems with known means and pairwise correlations physics.bio-ph · 2012 · author #3
  42. Efficient Methods for Unsupervised Learning of Probabilistic Models cs.LG · 2012 · author #1
  43. Hamiltonian Monte Carlo with Reduced Momentum Flips physics.data-an · 2012 · author #1
  44. Hamiltonian Annealed Importance Sampling for partition function estimation cs.LG · 2012 · author #1
  45. The Natural Gradient by Analogy to Signal Whitening, and Recipes and Tricks for its Use cs.LG · 2012 · author #1
  46. Efficient and optimal binary Hopfield associative memory storage using minimum probability flow nlin.AO · 2012 · author #2
  47. An Unsupervised Algorithm For Learning Lie Group Transformations cs.CV · 2010 · author #1
  48. Minimum Probability Flow Learning cs.LG · 2009 · author #1

Mentions

  • 1301.0050 #2 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1209.3744 #3 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1205.4295 #1 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1205.1939 #1 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1205.1925 #1 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1205.1828 #1 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1204.2916 #2 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 1001.1027 #1 · backfill · confidence 0.70 Jascha Sohl-Dickstein
  • 0906.4779 #1 · backfill · confidence 0.70 Jascha Sohl-Dickstein

Frequent Coauthors