• case-insensitive prefix search: default
  e.g., sig matches "SIGIR" as well as "signal"
• exact word search: append dollar sign ($) to word
  e.g., graph$ matches "graph", but not "graphics"
• boolean and: separate words by space
  e.g., codd model
• boolean or: connect words by pipe symbol (|)
  e.g., graph|network

Update May 7, 2017: Please note that we had to disable the phrase search operator (.) and the boolean not operator (-) due to technical problems. For the time being, phrase search queries will yield regular prefix search result, and search terms preceded by a minus will be interpreted as regular (positive) search terms.

found 161 matches

• 2024
• 
  Amirhesam Abedsoltan, Parthe Pandit, Luis Rademacher, Mikhail Belkin:
  On the Nyström Approximation for Preconditioning in Kernel Machines. AISTATS 2024: 3718-3726
• 
  James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin:
  More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory. ICLR 2024
• 
  Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin:
  Quadratic models for understanding catapult dynamics of neural networks. ICLR 2024
• 
  Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin:
  Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. ICML 2024
• 
  Adityanarayanan Radhakrishnan, Mikhail Belkin, Dmitriy Drusvyatskiy:
  Linear Recursive Feature Machines provably recover low-rank matrices. CoRR abs/2401.04553 (2024)
• 
  Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramón Huerta, Ivan Vulic:
  Unmemorization in Large Language Models via Self-Distillation and Deliberate Imagination. CoRR abs/2402.10052 (2024)
• 
  Daniel Beaglehole, Peter Súkeník, Marco Mondelli, Mikhail Belkin:
  Average gradient outer product as a mechanism for deep neural collapse. CoRR abs/2402.13728 (2024)
• 
  Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin:
  Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. CoRR abs/2407.20199 (2024)
• 2023
• 
  Pietro Patimisco, Nicoletta Ardito, Edoardo De Toma, Dominik Burghart, Vladislav Tigaev, Mikhail A. Belkin, Vincenzo Spagnolo:
  Quartz-Enhanced Photoacoustic Sensor Based on a Multi-Laser Source for In-Sequence Detection of NO2, SO2, and NH3. Sensors 23(21): 9005 (2023)
• 
  Daniel Beaglehole, Mikhail Belkin, Parthe Pandit:
  On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions. SIAM J. Math. Data Sci. 5(4): 854-872 (2023)
• 
  Nikhil Ghosh, Mikhail Belkin:
  A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors. SIAM J. Math. Data Sci. 5(4): 977-1004 (2023)
• 
  Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit:
  Toward Large Kernel Models. ICML 2023: 61-78
• 
  Like Hui, Mikhail Belkin, Stephen Wright:
  Cut your Losses with Squentropy. ICML 2023: 14114-14131
• 
  Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin:
  Neural tangent kernel at initialization: linear width suffices. UAI 2023: 110-118
• 
  Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit:
  Toward Large Kernel Models. CoRR abs/2302.02605 (2023)
• 
  Like Hui, Mikhail Belkin, Stephen Wright:
  Cut your Losses with Squentropy. CoRR abs/2302.03952 (2023)
• 
  Chaoyue Liu, Amirhesam Abedsoltan, Mikhail Belkin:
  On Emergence of Clean-Priority Learning in Early Stopped Neural Networks. CoRR abs/2306.02533 (2023)
• 
  Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yi-An Ma:
  Aiming towards the minimizers: fast convergence of SGD for overparametrized problems. CoRR abs/2306.02601 (2023)
• 
  Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin:
  Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. CoRR abs/2306.04815 (2023)
• 
  Daniel Beaglehole, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin:
  Mechanism of feature learning in convolutional neural networks. CoRR abs/2309.00570 (2023)
• 
  James B. Simon, Dhruva Karkada, Nikhil Ghosh, Mikhail Belkin:
  More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory. CoRR abs/2311.14646 (2023)
• 
  Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit, Luis Rademacher:
  On the Nystrom Approximation for Preconditioning in Kernel Machines. CoRR abs/2312.03311 (2023)
• 2022
• 
  Mikhail E. Belkin, Leonid Zhukov, Alexander S. Sigov:
  Advanced service data provisioning in ROF-based mobile backhauls/fronthauls. CoRR abs/2202.02458 (2022)
• 
  Yuan Cao, Zixiang Chen, Mikhail Belkin, Quanquan Gu:
  Benign Overfitting in Two-layer Convolutional Neural Networks. CoRR abs/2202.06526 (2022)
• 
  Like Hui, Mikhail Belkin, Preetum Nakkiran:
  Limitations of Neural Collapse for Understanding Generalization in Deep Learning. CoRR abs/2202.08384 (2022)
• 
  Chaoyue Liu, Libin Zhu, Mikhail Belkin:
  Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. CoRR abs/2203.05104 (2022)
• 
  Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler:
  Wide and Deep Neural Networks Achieve Optimality for Classification. CoRR abs/2204.14126 (2022)
• 
  Libin Zhu, Chaoyue Liu, Mikhail Belkin:
  Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. CoRR abs/2205.11786 (2022)
• 
  Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin:
  Quadratic models for understanding neural network dynamics. CoRR abs/2205.11787 (2022)
• 
  Daniel Beaglehole, Mikhail Belkin, Parthe Pandit:
  Kernel Ridgeless Regression is Inconsistent for Low Dimensions. CoRR abs/2205.13525 (2022)

skipping 131 more matches