Search Results for author:
Found 13 papers, 1 papers with code
A Tutorial Introduction to Reinforcement Learning
In this paper, we present a brief survey of Reinforcement Learning (RL), with particular emphasis on Stochastic Approximation (SA) as a unifying theme.
Convergence of Momentum-Based Heavy Ball Method with Batch Updating and/or Approximate Gradients
In this paper, we study the well-known "Heavy Ball" method for convex and nonconvex optimization introduced by Polyak in 1964, and establish its convergence under a variety of situations.
Estimating large causal polytrees from small samples
We consider the problem of estimating a large causal polytree from a relatively small i. i. d.
SUTRA: A Novel Approach to Modelling Pandemics with Applications to COVID-19
The Covid-19 pandemic has two key properties: (i) asymptomatic cases (both detected and undetected) that can result in new infections, and (ii) time-varying characteristics due to new variants, Non-Pharmaceutical Interventions etc.
New and Explicit Constructions of Unbalanced Ramanujan Bipartite Graphs
The objectives of this article are three-fold.
Deterministic Completion of Rectangular Matrices Using Asymmetric Ramanujan Graphs: Exact and Stable Recovery
By measuring a small number $m \ll n_r n_c$ of elements of $X$, is it possible to recover $X$ exactly with noise-free measurements, or to construct a good approximation of $X$ with noisy measurements?
Compressed Sensing Using Binary Matrices of Nearly Optimal Dimensions
Next we derive universal \textit{lower} bounds on the number of measurements that any binary matrix needs to have in order to satisfy the weaker sufficient condition based on the RNSP and show that bipartite graphs of girth six are optimal.
An Approach to One-Bit Compressed Sensing Based on Probably Approximately Correct Learning Theory
By coupling this estimate with well-established results in PAC learning theory, we show that a consistent algorithm can recover a $k$-sparse vector with $O(k \lg (n/k))$ measurements, given only the signs of the measurement vector.
A Fast Noniterative Algorithm for Compressive Sensing Using Binary Measurement Matrices
In this paper we present a new algorithm for compressive sensing that makes use of binary measurement matrices and achieves exact recovery of ultra sparse vectors, in a single pass and without any iterations.
Tight Performance Bounds for Compressed Sensing With Conventional and Group Sparsity
We introduce a new concept called group robust null space property (GRNSP), and show that, under suitable conditions, a group version of the restricted isometry property (GRIP) implies the GRNSP, and thus leads to group sparse recovery.
Two New Approaches to Compressed Sensing Exhibiting Both Robust Sparse Recovery and the Grouping Effect
It is shown here that SGL achieves robust sparse recovery, and also achieves a version of the grouping effect in that coefficients of highly correlated columns belonging to the same group of the measurement (or design) matrix are assigned roughly comparable values.
Machine Learning Methods in the Computational Biology of Cancer
As an illustration of the possibilities, a new algorithm for sparse regression is presented, and is applied to predict the time to tumor recurrence in ovarian cancer.
Near-Ideal Behavior of Compressed Sensing Algorithms
In a recent paper, it is shown that the LASSO algorithm exhibits "near-ideal behavior," in the following sense: Suppose $y = Az + \eta$ where $A$ satisfies the restricted isometry property (RIP) with a sufficiently small constant, and $\Vert \eta \Vert_2 \leq \epsilon$.
