activity
20162025
most citedInstability and Local Minima in GAN Training with Kernel Discriminators

5 citations · 23 across the 21 of their papers we have counts for

collaborators
Showing 2022Show all

6 papers · 1 filter

cs.LG2022

Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features

Adityanarayanan Radhakrishnan, Daniel Beaglehole, Parthe Pandit +1

In recent years neural networks have achieved impressive results on many technological and scientific tasks. Yet, the mechanism through which these models automatically select feat…

cs.LG2022★ 5 cited

Instability and Local Minima in GAN Training with Kernel Discriminators

Evan Becker, Parthe Pandit, Sundeep Rangan +1

Generative Adversarial Networks (GANs) are a widely-used tool for generative modeling of complex data. Despite their empirical success, the training of GANs is not fully understood…

cs.LG2022★ 3 cited

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

Neil Mallinar, James B. Simon, Amirhesam Abedsoltan +3

The practical success of overparameterized neural networks has motivated the recent scientific study of interpolating methods, which perfectly fit their training data. Certain inte…

cs.LG2022

A note on Linear Bottleneck networks and their Transition to Multilinearity

Libin Zhu, Parthe Pandit, Mikhail Belkin

Randomly initialized wide neural networks transition to linear functions of weights as the width grows, in a ball of radius around initialization. A necessary condition for…

cs.LG2022★ 1 cited

On the Inconsistency of Kernel Ridgeless Regression in Fixed Dimensions

Daniel Beaglehole, Mikhail Belkin, Parthe Pandit

``Benign overfitting'', the ability of certain algorithms to interpolate noisy training data and yet perform well out-of-sample, has been a topic of considerable recent interest. W…

stat.ML2022★ 1 cited

Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions

Mojtaba Sahraee-Ardakan, Melikasadat Emami, Parthe Pandit +2

Empirical observation of high dimensional phenomena, such as the double descent behaviour, has attracted a lot of interest in understanding classical techniques such as kernel meth…