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

Hanin, Boris

  1. Don't be lazy: CompleteP enables compute-efficient deep transformers
    2025/05/02 by Dey, Nolan, Bin Zhang, Zhang, Bin Claire +14 · 1 voice · 20 citations
    Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Parallel Computing and Optimization Techniques
  2. Neural Network Approximation
    2020/12/28 by DeVore, Ronald, Hanin, Boris, Petrova, Guergana · 14 citations
    #FOS: Mathematics #Numerical Analysis (math.NA)
  3. Complexity of Linear Regions in Deep Networks
    2019/01/25 by Hanin, Boris, Rolnick, David · 11 citations
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)
  4. Approximating Continuous Functions by ReLU Nets of Minimal Width
    2017/10/31 by Boris Hanin, Mark Sellke, Hanin, Boris +1 · 10 citations
    Computer Science · Engineering · #Advanced Neural Network Applications #Advanced Numerical Analysis Techniques #Combinatorics (math.CO) #Computational Complexity (cs.CC) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Statistics Theory (math.ST)
  5. Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
    2024/03/04 by Lingjiao Chen, Chen, Lingjiao, Jared Quincy Davis +11 · 17 citations
    Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Law #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Law, AI, and Intellectual Property #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering
  6. Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
    2024/10/11 by Noam Razin, Sadhika Malladi, Razin, Noam +10 · 4 voices · 10 citations
    Economics, Econometrics and Finance · #Economic and Environmental Valuation
  7. Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?
    2018/01/11 by Hanin, Boris · 6 citations
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR) #Statistics Theory (math.ST)
  8. Finite Depth and Width Corrections to the Neural Tangent Kernel
    2019/09/13 by Hanin, Boris, Nica, Mihai · 6 citations
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)
  9. Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
    2023/09/28 by Blake Bordelon, Bordelon, Blake, Lorenzo Noci +7 · 9 citations
    Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Cell Image Analysis Techniques #Disordered Systems and Neural Networks (cond-mat.dis-nn) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks
  10. How to Start Training: The Effect of Initialization and Architecture
    2018/03/05 by Hanin, Boris, Rolnick, David · 4 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
  11. Quantitative CLTs in Deep Neural Networks
    2023/07/12 by Stefano Favaro, Boris Hanin, Favaro, Stefano +7 · 6 citations
    Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Probability (math.PR) #Statistical Methods and Inference #Stochastic Gradient Optimization Techniques
  12. Optimizing Model Selection for Compound AI Systems
    2025/02/20 by Chen, Lingjiao, Davis, Jared Quincy, Hanin, Boris +4 · 8 citations
    #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA)
  13. Random Neural Networks in the Infinite Width Limit as Gaussian Processes
    2021/07/04 by Hanin, Boris · 2 citations
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Probability (math.PR) #Statistics Theory (math.ST)
  14. Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design
    2024/07/23 by Davis, Jared Quincy, Hanin, Boris, Chen, Lingjiao +3 · 3 citations
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences
  15. Pairing of Zeros and Critical Points for Random Polynomials
    2016/01/24 by Hanin, Boris · 1 citation
    #Complex Variables (math.CV) #FOS: Mathematics #FOS: Physical sciences #Mathematical Physics (math-ph) #Probability (math.PR)
  16. Local Universality for Zeros and Critical Points of Monochromatic Random\n Waves
    2016/10/28 by Yaiza Canzani, Canzani, Yaiza, Boris Hanin +1 · 1 citation
    Mathematics · #Geometry and complex manifolds #Geometric Analysis and Curvature Flows
  17. Deep ReLU Networks Preserve Expected Length
    2021/02/21 by Boris Hanin, Hanin, Boris, Ryan Jeong +3 · 2 citations
    Computer Science · #Adversarial Robustness in Machine Learning #Advanced Neural Network Applications #Neural Networks and Applications
  18. BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation
    2025/02/03 by Alan Zhu, Parth Asawa, Zhu, Alan +12 · 4 citations
    Computer Science · #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling
  19. Non-asymptotic Results for Singular Values of Gaussian Matrix Products
    2020/05/18 by Hanin, Boris, Paouris, Grigoris · 1 citation
    #FOS: Mathematics #FOS: Physical sciences #Mathematical Physics (math-ph) #Probability (math.PR)
  20. How Data Augmentation affects Optimization for Linear Regression
    2020/10/21 by Hanin, Boris, Sun, Yi · 1 citation
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
  21. Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies
    2022/04/03 by Hanin, Boris · 1 citation
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)
  22. Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
    2022/05/11 by Wuyang Chen, Wei Huang, Chen, Wuyang +7 · 1 citation
    Computer Science · Environmental Science · #Advanced Neural Network Applications #Air Quality Monitoring and Forecasting #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG)
  23. Maximal Initial Learning Rates in Deep ReLU Networks
    2022/12/14 by Gaurav Iyer, Boris Hanin, Iyer, Gaurav +3 · 1 citation
    Computer Science · #Advanced Neural Network Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Stochastic Gradient Optimization Techniques
  24. Bayesian Interpolation with Deep Linear Networks
    2022/12/29 by Hanin, Boris, Zlokapa, Alexander · 1 citation
    #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)
  25. Les Houches Lectures on Deep Learning at Large & Infinite Width
    2023/09/04 by Bahri, Yasaman, Hanin, Boris, Brossollet, Antonin +4 · 1 citation
    #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #FOS: Physical sciences #High Energy Physics - Theory (hep-th) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)