Posts by Collection



Sparse Regression and Support Recovery bounds for Orthogonal Matching Pursuit

Posted on:

We study the problem of sparse regression where the goal is to learn a sparse vector that best optimizes a given objective function. Under the assumption that the objective function satisfies restricted strong convexity (RSC), we analyze Orthogonal Matching Pursuit (OMP) and obtain support recovery result as well as a tight generalization error bound for OMP. Furthermore, we obtain lower bounds for OMP, showing that both our results on support recovery and generalization error are tight up to logarithmic factors. To the best of our knowledge, these support recovery and generalization bounds are the first such matching upper and lower bounds (up to logarithmic factors) for any sparse regression algorithm under the RSC assumption. Read more

Universality Patterns in the Training of Neural Networks

Posted on:

This work proposes and demonstrates a surprising pattern in the training of neural networks: there is a one to one relation between the values of any pair of losses (such as cross entropy, mean squared error, \(0/1\) error etc.) evaluated for a model arising at (any point of) a training run. This pattern is universal in the sense that this one to one relationship is identical across architectures (such as VGG, Resnet, Densenet etc.), algorithms (SGD and SGD with momentum) and training loss functions (cross entropy and mean squared error). Read more

Gradient flows on Graphons

Posted on:

Understanding scaling limits of gradient flow processes on large unlabeled graphs. This problem is motivated by the problem of optimizing permutation invariant risk functions of (single layer and deep) Neural Networks. Theoretical aspects stem from the original theory of gradient flows on the Wasserstein space, which have been used to understand scaling limits of (stochstic) gradient descent ((S)GD) processes in the case of single hidden layer neural networks. There are also other related questions that are specific to the qualitative nature of the stochasticity (sub-gaissian vs heavy tailed) in the SGD process. Read more


Non-Gaussianity of Stochastic Gradient Noise

Abhishek Panigrahi, Raghav Somani, Navin Goyal & Praneeth Netrapalli
Published at: Science meets Engineering of Deep Learning (SEDL) workshop, Neural Information Processing Systems (NeurIPS), 2019

We study the distribution of the Stochastic Gradient Noise during the training and observe that for batch sizes \(256\) and above, the distribution is best described as Gaussian at-least in the early phases of training. Read more

[arXiv] [bib]