vix.ing · top · new · best · stats · spec

Sohl-Dickstein, Jascha

  1. Levels of AGI for Operationalizing Progress on the Path to AGI
    2023/11/04 by Meredith Ringel Morris, Morris, Meredith Ringel, Jascha Sohl-Dickstein +13 · 16 voices · 18 citations
    #cs.AI
  2. Score-Based Generative Modeling through Stochastic Differential Equations
    2020/11/26 by Song, Yang, Sohl-Dickstein, Jascha, Kingma, Diederik P. +3 · 1 voice · 1246 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  3. Deep Unsupervised Learning using Nonequilibrium Thermodynamics
    2015/03/12 by Jascha Sohl‐Dickstein, Eric A. Weiss, Sohl-Dickstein, Jascha +5 · 773 citations
    Computer Science · Physics and Astronomy · #Advanced Thermodynamics and Statistical Mechanics #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Physical sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Neurons and Cognition (q-bio.NC)
  4. Exponential expressivity in deep neural networks through transient chaos
    2016/06/16 by Ben Poole, Poole, Ben, Subhaneil Lahiri +8 · 2 voices · 36 citations
    Computer Science · Mathematics · Neuroscience · Physics and Astronomy · #Model Reduction and Neural Networks #Neural Networks and Applications #Neural dynamics and brain function #cond-mat.dis-nn #cs.LG #stat.ML
  5. Density estimation using Real NVP
    2016/05/27 by Dinh, Laurent, Sohl-Dickstein, Jascha, Bengio, Samy · 166 citations
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
  6. The boundary of neural network trainability is fractal
    2024/02/09 by Jascha Sohl‐Dickstein, Jascha Sohl-Dickstein, Sohl-Dickstein, Jascha · 3 voices · 6 citations
    Computer Science · #Neural Networks and Applications
  7. Deep Knowledge Tracing
    2015/06/19 by Chris Piech, Piech, Chris, Jonathan Huang +10 · 52 citations
    Computer Science · #Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #K.3.1 #Machine Learning (cs.LG) #Online Learning and Analytics #Topic Modeling
  8. Deep Neural Networks as Gaussian Processes
    2017/11/01 by Jaehoon Lee, Lee, Jaehoon, Yasaman Bahri +9 · 57 citations
    Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Mechanics and Entropy #Target Tracking and Data Fusion in Sensor Networks
  9. Training LLMs over Neurally Compressed Text
    2024/04/04 by Brian Lester, Lester, Brian, Jaehoon Lee +12 · 4 voices · 2 citations
    Computer Science · #Handwritten Text Recognition Techniques #Mathematics, Computing, and Information Processing #Natural Language Processing Techniques #cs.CL #cs.LG
  10. Capacity and Trainability in Recurrent Neural Networks
    2016/11/29 by Jasmine Collins, Jascha Sohl‐Dickstein, Jascha Sohl-Dickstein +4 · 1 voice · 3 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Neural Networks and Applications #Stochastic Gradient Optimization Techniques #cs.AI #cs.LG #cs.NE #stat.ML
  11. On the Expressive Power of Deep Neural Networks
    2016/06/16 by Maithra Raghu, Raghu, Maithra, Ben Poole +7 · 37 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Neural Networks and Applications #Machine Learning and Algorithms
  12. Scaling Exponents Across Parameterizations and Optimizers
    2024/07/08 by Katie Everett, Lechao Xiao, Everett, Katie +19 · 2 voices · 18 citations
    #cs.LG
  13. Deep Information Propagation
    2016/11/04 by Schoenholz, Samuel S., Gilmer, Justin, Ganguli, Surya +1 · 19 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  14. Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
    2023/02/22 by Yilun Du, Du, Yilun, Conor Durkan +15 · 31 citations
    Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare #Topic Modeling
  15. Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
    2023/12/11 by Avi Singh, John D. Co-Reyes, Singh, Avi +76 · 35 citations
    Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Natural Language Processing Techniques #Topic Modeling
  16. Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
    2018/06/14 by Lechao Xiao, Xiao, Lechao, Yasaman Bahri +7 · 28 citations
    Computer Science · #Generative Adversarial Networks and Image Synthesis #Advanced Neural Network Applications #Human Pose and Action Recognition
  17. Sensitivity and Generalization in Neural Networks: an Empirical Study
    2018/02/23 by Roman Novak, Novak, Roman, Yasaman Bahri +7 · 18 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)
  18. Learned Optimizers that Scale and Generalize
    2017/03/14 by Olga Wichrowska, Wichrowska, Olga, Niru Maheswaranathan +11 · 15 citations
    Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Neural and Evolutionary Computing (cs.NE)
  19. Bayesian Deep Convolutional Networks with Many Channels are Gaussian\n Processes
    2018/10/11 by Roman Novak, Lechao Xiao, Novak, Roman +16 · 21 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Neural and Evolutionary Computing (cs.NE)
  20. The large learning rate phase of deep learning: the catapult mechanism
    2020/03/04 by Aitor Lewkowycz, Yasaman Bahri, Lewkowycz, Aitor +7 · 20 citations
    Computer Science · #Stochastic Gradient Optimization Techniques #Domain Adaptation and Few-Shot Learning #Neural Networks and Applications
  21. General-Purpose In-Context Learning by Meta-Learning Transformers
    2022/12/08 by Louis Kirsch, Kirsch, Louis, J. Harrison +5 · 14 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Neural and Evolutionary Computing (cs.NE)
  22. Unrolled Generative Adversarial Networks
    2016/11/07 by Luke Metz, Ben Poole, Metz, Luke +5 · 10 citations
    Computer Science · #Anomaly Detection Techniques and Applications #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  23. Neural Tangents: Fast and Easy Infinite Neural Networks in Python
    2019/12/05 by Roman Novak, Lechao Xiao, Novak, Roman +11 · 11 citations
    Physics and Astronomy · Computer Science · #Model Reduction and Neural Networks #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning
  24. Infinite attention: NNGP and NTK for deep attention networks
    2020/06/18 by Hron, Jiri, Bahri, Yasaman, Sohl-Dickstein, Jascha +1 · 8 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  25. Finite Versus Infinite Neural Networks: an Empirical Study
    2020/07/31 by Lee, Jaehoon, Schoenholz, Samuel S., Pennington, Jeffrey +4 · 6 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  26. Understanding and correcting pathologies in the training of learned optimizers
    2018/10/24 by Metz, Luke, Maheswaranathan, Niru, Nixon, Jeremy +2 · 5 citations
    #FOS: Computer and information sciences #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
  27. Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
    2013/11/08 by Jascha Sohl‐Dickstein, Jascha Sohl-Dickstein, Sohl-Dickstein, Jascha +4 · 1 voice · 3 citations
    Computer Science · Engineering · #90C26 #Advanced Image Processing Techniques #FOS: Computer and information sciences #G.1.6 #Machine Learning (cs.LG) #Neural Networks and Applications #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques #cs.LG
  28. Fast Finite Width Neural Tangent Kernel
    2022/06/17 by Roman Novak, Novak, Roman, Jascha Sohl‐Dickstein +3 · 7 citations
    Physics and Astronomy · Computer Science · #Model Reduction and Neural Networks #Neural Networks and Applications #Human Pose and Action Recognition
  29. A Correspondence Between Random Neural Networks and Statistical Field\n Theory
    2017/10/17 by Samuel S. Schoenholz, Jeffrey Pennington, Schoenholz, Samuel S. +3 · 4 citations
    Computer Science · Physics and Astronomy · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Statistical Mechanics and Entropy
  30. VeLO: Training Versatile Learned Optimizers by Scaling Up
    2022/11/17 by Luke Metz, James Harrison, Metz, Luke +22 · 2 voices · 4 citations
    Computer Science · #Advanced Neural Network Applications #Human Pose and Action Recognition #Machine Learning and Data Classification #cs.LG #math.OC #stat.ML
  31. A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
    2022/09/22 by Harrison, James, Metz, Luke, Sohl-Dickstein, Jascha · 5 citations
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
  32. REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
    2017/03/21 by Tucker, George, Mnih, Andriy, Maddison, Chris J. +2 · 3 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  33. NL-Augmenter: A Framework for Task-Sensitive Natural Language\n Augmentation
    2021/12/05 by Kaustubh Dhole, Varun Gangal, Dhole, Kaustubh D. +221 · 4 citations
    Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications
  34. On the infinite width limit of neural networks with a standard\n parameterization
    2020/01/20 by Jascha Sohl‐Dickstein, Sohl-Dickstein, Jascha, Roman Novak +5 · 4 citations
    Computer Science · Physics and Astronomy · #Neural Networks and Applications #Advanced Neural Network Applications #Model Reduction and Neural Networks
  35. Tasks, stability, architecture, and compute: Training more effective\n learned optimizers, and using them to train themselves
    2020/09/23 by Luke Metz, Niru Maheswaranathan, Metz, Luke +7 · 4 citations
    Computer Science · #Advanced Multi-Objective Optimization Algorithms #Advanced Neural Network Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)
  36. Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
    2020/03/12 by Che, Tong, Zhang, Ruixiang, Sohl-Dickstein, Jascha +4 · 3 citations
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  37. A new method for parameter estimation in probabilistic models: Minimum probability flow
    2020/07/17 by Sohl-Dickstein, Jascha, Battaglino, Peter, DeWeese, Michael R. · 3 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  38. Efficient and optimal binary Hopfield associative memory storage using minimum probability flow
    2012/04/13 by Hillar, Christopher, Sohl-Dickstein, Jascha, Koepsell, Kilian · 2 citations
    #Adaptation and Self-Organizing Systems (nlin.AO) #FOS: Biological sciences #FOS: Physical sciences #Neurons and Cognition (q-bio.NC)
  39. Data files for "Neural reparameterization improves structural optimization"
    2019/09/10 by Stephan Hoyer, Jascha Sohl‐Dickstein, Hoyer, Stephan +3 · 3 citations
    Computer Science · Engineering · #Advanced Multi-Objective Optimization Algorithms #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE) #Structural Health Monitoring Techniques #Topology Optimization in Engineering
  40. Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
    2021/12/27 by Vicol, Paul, Metz, Luke, Sohl-Dickstein, Jascha · 3 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  41. Improved generator objectives for GANs
    2016/12/08 by Poole, Ben, Alemi, Alexander A., Sohl-Dickstein, Jascha +1 · 2 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  42. Practical tradeoffs between memory, compute, and performance in learned optimizers
    2022/03/22 by Luke Metz, Metz, Luke, C. Daniel Freeman +7 · 3 citations
    Computer Science · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification #Metaheuristic Optimization Algorithms Research #Neural and Evolutionary Computing (cs.NE) #Optimization and Control (math.OC)
  43. Meta-Learning Update Rules for Unsupervised Representation Learning
    2018/03/31 by Metz, Luke, Maheswaranathan, Niru, Cheung, Brian +1 · 2 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
  44. Using a thousand optimization tasks to learn hyperparameter search strategies
    2020/02/27 by Metz, Luke, Maheswaranathan, Niru, Sun, Ruoxi +3 · 2 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  45. Exact posterior distributions of wide Bayesian neural networks
    2020/06/18 by Hron, Jiri, Bahri, Yasaman, Novak, Roman +2 · 2 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  46. Reverse engineering learned optimizers reveals known and novel mechanisms
    2020/11/04 by Maheswaranathan, Niru, Sussillo, David, Metz, Luke +2 · 2 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
  47. Minimum Probability Flow Learning
    2009/06/25 by Jascha Sohl‐Dickstein, Sohl-Dickstein, Jascha, Peter Battaglino +3 · 1 citation
    Computer Science · #Data Analysis #FOS: Computer and information sciences #FOS: Physical sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Statistics and Probability (physics.data-an)
  48. The Natural Gradient by Analogy to Signal Whitening, and Recipes and Tricks for its Use
    2012/05/08 by Sohl-Dickstein, Jascha · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  49. Analyzing noise in autoencoders and deep networks
    2014/06/06 by Poole, Ben, Sohl-Dickstein, Jascha, Ganguli, Surya · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
  50. A Mean Field Theory of Batch Normalization
    2019/02/21 by Yang, Greg, Pennington, Jeffrey, Rao, Vinay +2 · 1 citation
    #Disordered Systems and Neural Networks (cond-mat.dis-nn) #Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Mathematics #FOS: Physical sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
  51. The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study
    2019/05/09 by Park, Daniel S., Sohl-Dickstein, Jascha, Le, Quoc V. +1 · 1 citation
    #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  52. Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization
    2020/08/17 by Wadia, Neha S., Duckworth, Daniel, Schoenholz, Samuel S. +2 · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  53. Hamiltonian Annealed Importance Sampling for partition function\n estimation
    2012/05/09 by Jascha Sohl‐Dickstein, Benjamin J. Culpepper, Sohl-Dickstein, Jascha +2 · 1 citation
    Computer Science · Mathematics · #Bayesian Methods and Mixture Models #Bayesian Modeling and Causal Inference #Data Analysis #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Markov Chains and Monte Carlo Methods #Statistical Methods and Inference #Statistics and Probability (physics.data-an)
  54. Survey of Expressivity in Deep Neural Networks
    2016/11/24 by Maithra Raghu, Ben Poole, Raghu, Maithra +7 · 1 voice
    Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE) #cs.LG #cs.NE #stat.ML
  55. Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
    2022/06/15 by Hron, Jiri, Novak, Roman, Pennington, Jeffrey +1 · 1 citation
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  56. Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping
    2021/10/05 by Martens, James, Ballard, Andy, Desjardins, Guillaume +4 · 1 citation
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
  57. Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
    2023/04/21 by Li, Oscar, Harrison, James, Sohl-Dickstein, Jascha +2 · 1 citation
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)