Atish Agarwala

1. Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
   2025/07/02 by Shikai Qiu, Lechao Xiao, Qiu, Shikai +7 · 3 voices · 11 citations
   #cs.LG
2. Second-order regression models exhibit progressive sharpening to the edge of stability
   2022/10/10 by Atish Agarwala, Fabián Pedregosa, Agarwala, Atish +3 · 3 citations
   Computer Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications #Optimization and Control (math.OC) #Stochastic Gradient Optimization Techniques
3. SAM operates far from home: eigenvalue regularization as a dynamical phenomenon
   2023/02/17 by Atish Agarwala, Yann Dauphin, Agarwala, Atish +1 · 3 citations
   Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Neural Networks and Applications
4. Deep equilibrium networks are sensitive to initialization statistics
   2022/07/19 by Atish Agarwala, Agarwala, Atish, Samuel S. Schoenholz +1 · 2 citations
   Neuroscience · Physics and Astronomy · #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Machine Learning (cs.LG) #Neural dynamics and brain function #Quantum many-body systems
5. Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
   2024/02/07 by Daniel Beaglehole, Ioannis Mitliagkas, Beaglehole, Daniel +3 · 2 citations
   Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #Brain Tumor Detection and Classification #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Neural Networks and Applications
6. Avoiding spurious sharpness minimization broadens applicability of SAM
   2025/02/04 by Sidak Pal Singh, Singh, Sidak Pal, Hossein Mobahi +5 · 1 voice · 2 citations
   Computer Science · Mathematics · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.CL #cs.LG #stat.ML
7. How far away are truly hyperparameter-free learning algorithms?
   2025/05/29 by Priya Kasimbeg, Kasimbeg, Priya, Vincent Roulet +11 · 1 voice · 1 citation
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification #Neural Networks and Applications #cs.LG