Sudeep Salgia
YOU?
Author Swipe
View article: Differential Privacy in Kernelized Contextual Bandits via Random Projections
Differential Privacy in Kernelized Contextual Bandits via Random Projections Open
We consider the problem of contextual kernel bandits with stochastic contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space. We study this problem under an additional constraint of Differential P…
View article: Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization Open
We consider the problem of differentially private stochastic convex optimization (DP-SCO) in a distributed setting with $M$ clients, where each of them has a local dataset of $N$ i.i.d. data samples from an underlying data distribution. Th…
View article: Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness
Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness Open
We consider distributed kernel bandits where $N$ agents aim to collaboratively maximize an unknown reward function that lies in a reproducing kernel Hilbert space. Each agent sequentially queries the function to obtain noisy observations a…
View article: Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency
Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency Open
We consider Bayesian optimization using Gaussian Process models, also referred to as kernel-based bandit optimization. We study the methodology of exploring the domain using random samples drawn from a distribution. We show that this rando…
View article: A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret
A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret Open
We consider the problem of online stochastic optimization in a distributed setting with $M$ clients connected through a central server. We develop a distributed online learning algorithm that achieves order-optimal cumulative regret with l…
View article: Distributed Linear Bandits under Communication Constraints
Distributed Linear Bandits under Communication Constraints Open
We consider distributed linear bandits where $M$ agents learn collaboratively to minimize the overall cumulative regret incurred by all agents. Information exchange is facilitated by a central server, and both the uplink and downlink commu…
View article: A perspective on data sharing in digital food safety systems
A perspective on data sharing in digital food safety systems Open
In this age of data, digital tools are widely promoted as having tremendous potential for enhancing food safety. However, the potential of these digital tools depends on the availability and quality of data, and a number of obstacles need …
View article: Collaborative Learning in Kernel-based Bandits for Distributed Users
Collaborative Learning in Kernel-based Bandits for Distributed Users Open
We study collaborative learning among distributed clients facilitated by a central server. Each client is interested in maximizing a personalized objective function that is a weighted sum of its local objective and a global objective. Each…
View article: Provably and Practically Efficient Neural Contextual Bandits
Provably and Practically Efficient Neural Contextual Bandits Open
We consider the neural contextual bandit problem. In contrast to the existing work which primarily focuses on ReLU neural nets, we consider a general set of smooth activation functions. Under this more general setting, (i) we derive non-as…
View article: As Easy as ABC: Adaptive Binning Coincidence Test for Uniformity Testing
As Easy as ABC: Adaptive Binning Coincidence Test for Uniformity Testing Open
We consider the problem of uniformity testing of Lipschitz continuous distributions with bounded support. The alternative hypothesis is a composite set of Lipschitz continuous distributions that are at least $\varepsilon$ away in $\ell_1$ …
View article: A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance
A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance Open
We consider sequential optimization of an unknown function in a reproducing kernel Hilbert space. We propose a Gaussian process-based algorithm and establish its order-optimal regret performance (up to a poly-logarithmic factor). This is t…
View article: A Computationally Efficient Approach to Black-box Optimization using Gaussian Process Models.
A Computationally Efficient Approach to Black-box Optimization using Gaussian Process Models. Open
We consider sequential optimization of an unknown function under Gaussian process models. We develop a computationally efficient algorithm that reduces the complexity of the prevailing GP-UCB family of algorithms by a factor of $O(T^{2d-1}…
View article: Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization
Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization Open
A framework based on iterative coordinate minimization (CM) is developed for stochastic convex optimization. Given that exact coordinate minimization is impossible due to the unknown stochastic nature of the objective function, the crux of…
View article: Disagreement-based Active Learning in Online Settings
Disagreement-based Active Learning in Online Settings Open
We study online active learning for classifying streaming instances within the framework of statistical learning theory. At each time, the learner either queries the label of the current instance or predicts the label based on past seen ex…
View article: Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization
Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization Open
Online minimization of an unknown convex function over the interval $[0,1]$ is considered under first-order stochastic bandit feedback, which returns a random realization of the gradient of the function at each query point. Without knowing…
View article: Bandlimited Spatiotemporal Field Sampling with Location and Time Unaware Mobile Sensors
Bandlimited Spatiotemporal Field Sampling with Location and Time Unaware Mobile Sensors Open
Sampling of a spatiotemporal field for environmental sensing is of interest. Traditionally, a few fixed stations or sampling locations aid in the reconstruction of the spatial field. Recently, there has been an interest in mobile sensing a…
View article: On Bandlimited Spatiotemporal Field Sampling with Location and Time\n Unaware Mobile Sensors
On Bandlimited Spatiotemporal Field Sampling with Location and Time\n Unaware Mobile Sensors Open
Sampling of a spatiotemporal field for environmental sensing is of interest.\nTraditionally, a few fixed stations or sampling locations aid in the\nreconstruction of the spatial field. Recently, there has been an interest in\nmobile sensin…
View article: Spatial Field estimation from Samples taken at Unknown Locations generated by an Unknown Autoregressive Process
Spatial Field estimation from Samples taken at Unknown Locations generated by an Unknown Autoregressive Process Open
Sampling of physical fields with mobile sensors is an upcoming field of interest. This offers greater advantages in terms of cost as often just a single sensor can be used for the purpose and this can be employed almost everywhere without …