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

Daniel Kunin

  1. There Will Be a Scientific Theory of Deep Learning
    2026/04/23 by Jamie Simon, Daniel Kunin, Alexander Atanasov +11 · 31 voices · 1 citation
    #stat.ML #cs.LG
  2. Pruning neural networks without any data by iteratively conserving synaptic flow
    2020/06/09 by Hidenori Tanaka, Daniel Kunin, Daniel L. K. Yamins +1 · 1 voice · 30 citations
    #cs.LG #cond-mat.dis-nn #cs.CV #q-bio.NC #stat.ML
  3. From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
    2024/09/22 by Clémentine C. J. Dominé, Clémentine Dominé, Dominé, Clémentine C. J. +13 · 1 voice · 15 citations
    Computer Science · #Neural Networks and Applications
  4. Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
    2024/06/10 by Daniel Kunin, Allan Raventós, Kunin, Daniel +11 · 4 voices · 6 citations
    Computer Science · #Machine Learning and Data Classification
  5. Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning\n Dynamics
    2020/12/08 by Daniel Kunin, Javier Sagastuy-Breña, Kunin, Daniel +7 · 10 citations
    Computer Science · #Stochastic Gradient Optimization Techniques #Adversarial Robustness in Machine Learning #Generative Adversarial Networks and Image Synthesis
  6. Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
    2023/06/07 by Feng Chen, Daniel Kunin, Chen, Feng +5 · 7 citations
    Computer Science · #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Stochastic Gradient Optimization Techniques
  7. Two Routes to Scalable Credit Assignment without Weight Symmetry
    2020/02/28 by Daniel Kunin, Kunin, Daniel, Aran Nayebi +9 · 3 citations
    Computer Science · Engineering · #Advanced Memory and Neural Computing #Domain Adaptation and Few-Shot Learning #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Neural and Evolutionary Computing (cs.NE) #Neurons and Cognition (q-bio.NC)
  8. Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes
    2022/04/24 by Chao Ma, Daniel Kunin, Ma, Chao +5 · 2 citations
    Computer Science · Biochemistry, Genetics and Molecular Biology · Physics and Astronomy · #Advanced Mathematical Modeling in Engineering #Advanced Electron Microscopy Techniques and Applications #Model Reduction and Neural Networks