9 citations · 35 across the 23 of their papers we have counts for
12 papers · 1 filter
Mirror Descent on Reproducing Kernel Banach Spaces
Akash Kumar, Mikhail Belkin, Parthe Pandit
Recent advances in machine learning have led to increased interest in reproducing kernel Banach spaces (RKBS) as a more general framework that extends beyond reproducing kernel Hil…
Local Convergence of Gradient Descent-Ascent for Training Generative Adversarial Networks
Evan Becker, Parthe Pandit, Sundeep Rangan +1
Generative Adversarial Networks (GANs) are a popular formulation to train generative models for complex high dimensional data. The standard method for training GANs involves a grad…
Toward Large Kernel Models
Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit
Recent studies indicate that kernel machines can often perform similarly or better than deep neural networks (DNNs) on small datasets. The interest in kernel machines has been addi…
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…
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…
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…
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…
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…
Implicit Bias of Linear RNNs
Melikasadat Emami, Mojtaba Sahraee-Ardakan, Parthe Pandit +2
Contemporary wisdom based on empirical studies suggests that standard recurrent neural networks (RNNs) do not perform well on tasks requiring long-term memory. However, precise rea…
Generalization Error of Generalized Linear Models in High Dimensions
Melikasadat Emami, Mojtaba Sahraee-Ardakan, Parthe Pandit +2
At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are no…
Inference in Multi-Layer Networks with Matrix-Valued Unknowns
Parthe Pandit, Mojtaba Sahraee-Ardakan, Sundeep Rangan +2
We consider the problem of inferring the input and hidden variables of a stochastic multi-layer neural network from an observation of the output. The hidden variables in each layer…
Inference with Deep Generative Priors in High Dimensions
Parthe Pandit, Mojtaba Sahraee-Ardakan, Sundeep Rangan +2
Deep generative priors offer powerful models for complex-structured data, such as images, audio, and text. Using these priors in inverse problems typically requires estimating the…