Adityanarayanan Radhakrishnan

According to our database, Adityanarayanan Radhakrishnan authored at least 22 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product.

Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin

CoRR, 2024

Linear Recursive Feature Machines provably recover low-rank matrices.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Dmitriy Drusvyatskiy

CoRR, 2024

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Quadratic models for understanding catapult dynamics of neural networks.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Foundations of Machine Learning: Over-parameterization and Feature Learning

Adityanarayanan Radhakrishnan

PhD thesis, 2023

Mechanism of feature learning in convolutional neural networks.

Daniel Beaglehole, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin

CoRR, 2023

2022

Feature learning in neural networks and kernel machines that recursively learn features.

Adityanarayanan Radhakrishnan, Daniel Beaglehole, Parthe Pandit, Mikhail Belkin

CoRR, 2022

Transfer Learning with Kernel Methods.

Adityanarayanan Radhakrishnan, Max Ruiz Luyten, Neha Prasad, Caroline Uhler

CoRR, 2022

Quadratic models for understanding neural network dynamics.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

CoRR, 2022

Wide and Deep Neural Networks Achieve Optimality for Classification.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2022

2021

Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2021

Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks.

Adityanarayanan Radhakrishnan, George Stefanakis, Mikhail Belkin, Caroline Uhler

CoRR, 2021

A Mechanism for Producing Aligned Latent Spaces with Autoencoders.

Saachi Jain, Adityanarayanan Radhakrishnan, Caroline Uhler

CoRR, 2021

2020

Overparameterized neural networks implement associative memory.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

Proc. Natl. Acad. Sci. USA, 2020

Do Deeper Convolutional Networks Perform Better?

Eshaan Nichani, Adityanarayanan Radhakrishnan, Caroline Uhler

CoRR, 2020

Linear Convergence and Implicit Regularization of Generalized Mirror Descent with Time-Dependent Mirrors.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2020

Balancedness and Alignment are Unlikely in Linear Neural Networks.

Adityanarayanan Radhakrishnan, Eshaan Nichani, Daniel Irving Bernstein, Caroline Uhler

CoRR, 2020

2019

Overparameterized Neural Networks Can Implement Associative Memory.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2019

2018

Counting Markov equivalence classes for DAG models on trees.

Adityanarayanan Radhakrishnan, Liam Solus, Caroline Uhler

Discret. Appl. Math., 2018

Downsampling leads to Image Memorization in Convolutional Autoencoders.

Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

CoRR, 2018

2017

Patchnet: Interpretable Neural Networks for Image Classification.

Adityanarayanan Radhakrishnan, Charles Durham, Ali Soylemezoglu, Caroline Uhler

CoRR, 2017

Counting Markov Equivalence Classes by Number of Immoralities.

Adityanarayanan Radhakrishnan, Liam Solus, Caroline Uhler

Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence, 2017