32 citations · 50 across the 5 of their papers we have counts for
9 papers
The Dynamics of Gradient Descent for Overparametrized Neural Networks
Siddhartha Satpathi, R Srikant
We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under som…
Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation
Semih Cayci, Siddhartha Satpathi, Niao He +1
In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD lear…
Learning Latent Events from Network Message Logs
Siddhartha Satpathi, Supratim Deb, R Srikant +1
We consider the problem of separating error messages generated in large distributed data center networks into error events. In such networks, each error event leads to a stream of…
A Modified Multiple OLS (mOLS) Algorithm for Signal Recovery in Compressive Sensing
Samrat Mukhopadhyay, Siddhartha Satpathi, Mrityunjoy Chakraborty
Orthogonal least square (OLS) is an important sparse signal recovery algorithm for compressive sensing, which enjoys superior probability of success over other well-known recovery…
Optimal Offline and Competitive Online Strategies for Transmitter-Receiver Energy Harvesting
Siddhartha Satpathi, Rushil Nagda, Rahul Vaze
A joint transmitter-receiver energy harvesting model is considered, where both the transmitter and receiver are powered by (renewable) energy harvesting source. Given a fixed numbe…
Optimal Offline and Competitive Online Strategies for Transmitter-Receiver Energy Harvesting
Rushil Nagda, Siddharth Satpathi, Rahul Vaze
Transmitter-receiver energy harvesting model is assumed, where both the transmitter and receiver are powered by random energy source. Given a fixed number of bits, the problem is t…
On the Number of Iterations for Convergence of CoSaMP and Subspace Pursuit Algorithms
Siddhartha Satpathi, Mrityunjoy Chakraborty
In compressive sensing, one important parameter that characterizes the various greedy recovery algorithms is the iteration bound which provides the maximum number of iterations by…
Group-Sparse Model Selection: Hardness and Relaxations
Luca Baldassarre, Nirav Bhan, Volkan Cevher +2
Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. The main pr…
Improved Bounds on RIP for Generalized Orthogonal Matching Pursuit
Siddhartha Satpathi, Rajib Lochan Das, Mrityunjoy Chakraborty
Generalized Orthogonal Matching Pursuit (gOMP) is a natural extension of OMP algorithm where unlike OMP, it may select atoms in each iteration. In this paper, we demons…