Roberts, Daniel A.
- Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
2024/04/01 by Matthias Gerstgrasser, Rylan Schaeffer, Gerstgrasser, Matthias +26 · 16 voices · 31 citations
Computer Science · #Semantic Web and Ontologies #cs.AI #cs.CL #cs.ET #cs.LG #stat.ML
- Why is AI hard and Physics simple?
2021/03/31 by Daniel A. Roberts, Roberts, Daniel A. · 4 voices · 1 citation
Computer Science · Physics and Astronomy · #Computational Physics and Python Applications #Statistical Mechanics and Entropy #Gaussian Processes and Bayesian Inference
- The Unreasonable Ineffectiveness of the Deeper Layers
2024/03/26 by Andrey Gromov, Kushal Tirumala, Gromov, Andrey +7 · 4 voices · 35 citations
Computer Science · #Advanced Neural Network Applications #Multimodal Machine Learning Applications #Topic Modeling #cs.CL #cs.LG #stat.ML
- Gradient Descent Happens in a Tiny Subspace
2018/12/12 by Guy Gur-Ari, Daniel A. Roberts, Gur-Ari, Guy +3 · 39 citations
Computer Science · #Stochastic Gradient Optimization Techniques #Gaussian Processes and Bayesian Inference #Domain Adaptation and Few-Shot Learning
- A Solvable Model of Neural Scaling Laws
2022/10/30 by Alexander Maloney, Maloney, Alexander, Daniel A. Roberts +3 · 18 citations
Computer Science · #FOS: Computer and information sciences #FOS: Physical sciences #High Energy Physics - Theory (hep-th) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Neural Networks and Applications #Topic Modeling
- Robust Learning with Jacobian Regularization
2019/08/07 by Hoffman, Judy, Roberts, Daniel A., Yaida, Sho · 12 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Feature Learning and Generalization in Deep Networks with Orthogonal Weights
2023/10/11 by H. Michael Day, Day, Hannah, Yonatan Kahn +3 · 2 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Physical sciences #High Energy Physics - Phenomenology (hep-ph) #High Energy Physics - Theory (hep-th) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications