Adityanarayanan Radhakrishnan

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 21

Top Topics

Stochastic Gradient Descent

Top Venues

Discret. Appl. Math.

Proc. Natl. Acad. Sci. USA

Publications

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
Quadratic models for understanding catapult dynamics of neural networks. ICLR (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 (2024)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Dmitriy Drusvyatskiy
Linear Recursive Feature Machines provably recover low-rank matrices. CoRR (2024)
Daniel Beaglehole, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
Mechanism of feature learning in convolutional neural networks. CoRR (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 (2023)
Adityanarayanan Radhakrishnan, Max Ruiz Luyten, Neha Prasad, Caroline Uhler
Transfer Learning with Kernel Methods. CoRR (2022)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Wide and Deep Neural Networks Achieve Optimality for Classification. CoRR (2022)
Adityanarayanan Radhakrishnan, Daniel Beaglehole, Parthe Pandit, Mikhail Belkin
Feature learning in neural networks and kernel machines that recursively learn features. CoRR (2022)
Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
Quadratic models for understanding neural network dynamics. CoRR (2022)
Adityanarayanan Radhakrishnan, George Stefanakis, Mikhail Belkin, Caroline Uhler
Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks. CoRR (2021)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size. CoRR (2021)
Saachi Jain, Adityanarayanan Radhakrishnan, Caroline Uhler
A Mechanism for Producing Aligned Latent Spaces with Autoencoders. CoRR (2021)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors. CoRR (2020)
Eshaan Nichani, Adityanarayanan Radhakrishnan, Caroline Uhler
Do Deeper Convolutional Networks Perform Better? CoRR (2020)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Overparameterized neural networks implement associative memory. Proc. Natl. Acad. Sci. USA 117 (44) (2020)
Adityanarayanan Radhakrishnan, Eshaan Nichani, Daniel Irving Bernstein, Caroline Uhler
Balancedness and Alignment are Unlikely in Linear Neural Networks. CoRR (2020)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Overparameterized Neural Networks Can Implement Associative Memory. CoRR (2019)
Adityanarayanan Radhakrishnan, Liam Solus, Caroline Uhler
Counting Markov equivalence classes for DAG models on trees. Discret. Appl. Math. 244 (2018)
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Downsampling leads to Image Memorization in Convolutional Autoencoders. CoRR (2018)
Adityanarayanan Radhakrishnan, Charles Durham, Ali Soylemezoglu, Caroline Uhler
Patchnet: Interpretable Neural Networks for Image Classification. CoRR (2017)
Adityanarayanan Radhakrishnan, Liam Solus, Caroline Uhler
Counting Markov Equivalence Classes by Number of Immoralities. UAI (2017)