Sagun, Levent

1. Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
   2016/11/06 by Pratik Chaudhari, Chaudhari, Pratik, Anna Choromanska +15 · 48 citations
   Physics and Astronomy · Computer Science · #Model Reduction and Neural Networks #Stochastic Gradient Optimization Techniques #Advanced Neural Network Applications
2. Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
   2017/06/14 by Levent Sagun, Utku Evci, Sagun, Levent +7 · 42 citations
   Computer Science · Engineering · Mathematics · #Stochastic Gradient Optimization Techniques #Sparse and Compressive Sensing Techniques #Random Matrices and Applications
3. Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
   2016/11/22 by Levent Sagun, Sagun, Levent, Léon Bottou +3 · 29 citations
   Computer Science · Physics and Astronomy · #Stochastic Gradient Optimization Techniques #Model Reduction and Neural Networks #Gaussian Processes and Bayesian Inference
4. A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
   2019/01/18 by Simsekli, Umut, Sagun, Levent, Gurbuzbalaban, Mert · 23 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
5. SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
   2017/04/18 by Dunn, Matthew, Sagun, Levent, Higgins, Mike +3 · 11 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences
6. On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
   2019/11/29 by Umut Şimşekli, Mert Gürbüzbalaban, Şimşekli, Umut +7 · 8 citations
   Computer Science · Engineering · #Stochastic Gradient Optimization Techniques #Sparse and Compressive Sensing Techniques #Adversarial Robustness in Machine Learning
7. Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
   2022/02/16 by Goyal, Priya, Duval, Quentin, Seessel, Isaac +5 · 2 citations
   #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #FOS: Computer and information sciences
8. Transformed CNNs: recasting pre-trained convolutional layers with self-attention
   2021/06/10 by d'Ascoli, Stéphane, Sagun, Levent, Biroli, Giulio +1 · 1 citation
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
9. Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
   2019/06/16 by Stéphane d’Ascoli, d'Ascoli, Stéphane, Levent Sagun +5 · 2 citations
   Computer Science · #Advanced Neural Network Applications #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Statistical Mechanics (cond-mat.stat-mech) #Stochastic Gradient Optimization Techniques
10. Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction
    2023/09/29 by Arjun Subramonian, Levent Sagun, Subramonian, Arjun +3 · 1 citation
    Physics and Astronomy · Psychology · #Complex Network Analysis Techniques #Opinion Dynamics and Social Influence #Mental Health Research Topics
11. Chained Tuning Leads to Biased Forgetting
    2024/12/21 by Megan Ung, Ung, Megan, Sun, Alicia +8 · 1 citation
    Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences