arXiv subjects

Sudeep Salgia

Publications and source records attributed to Sudeep Salgia.

17 recordsLinked to original sources

arXiv2025

Differential Privacy in Kernelized Contextual Bandits via Random Projections

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 Privacy, where the agent needs to ensure that the sequence of query points is differentially private with respect to both the sequence of contexts and rewards. We propose a novel algorithm that achieves the state-of-the-art cumulative regret of $\widetilde{\mathcal{O}}(\sqrt{\gamma_TT}+\frac{\gamma_T}{\varepsilon_{\mathrm{DP}}})$ and $\widetilde{\mathcal{O}}(\sqrt{\gamma_TT}+\frac{\gamma_T\sqrt{T}}{\varepsilon_{\mathrm{DP}}})$ over a time horizon of $T$ in the joint and local models of differential privacy, respectively, where $\gamma_T$ is the effective dimension of the kernel and $\varepsilon_{\mathrm{DP}} > 0$ is the privacy parameter. The key ingredient of the proposed algorithm is a novel private kernel-ridge regression estimator which is based on a combination of private covariance estimation and private random projections. It offers a significantly reduced sensitivity compared to its classical counterpart while maintaining a high prediction accuracy, allowing our algorithm to achieve the state-of-the-art performance guarantees.

stat.ML↗

arXiv2025

Differentially Private Kernelized Contextual Bandits

We consider the problem of contextual kernel bandits with stochastic contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space (RKHS). We study this problem under the additional constraint of joint differential privacy, where the agents needs to ensure that the sequence of query points is differentially private with respect to both the sequence of contexts and rewards. We propose a novel algorithm that improves upon the state of the art and achieves an error rate of $\mathcal{O}\left(\sqrt{\frac{\gamma_T}{T}} + \frac{\gamma_T}{T \varepsilon}\right)$ after $T$ queries for a large class of kernel families, where $\gamma_T$ represents the effective dimensionality of the kernel and $\varepsilon > 0$ is the privacy parameter. Our results are based on a novel estimator for the reward function that simultaneously enjoys high utility along with a low-sensitivity to observed rewards and contexts, which is crucial to obtain an order optimal learning performance with improved dependence on the privacy parameter.

stat.ML↗

arXiv2025

Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization

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. The objective is to design an algorithm to minimize a convex population loss using a collaborative effort across $M$ clients, while ensuring the privacy of the local datasets. In this work, we investigate the accuracy-communication-privacy trade-off for this problem. We establish matching converse and achievability results using a novel lower bound and a new algorithm for distributed DP-SCO based on Vaidya's plane cutting method. Thus, our results provide a complete characterization of the accuracy-communication-privacy trade-off for DP-SCO in the distributed setting.

cs.LG↗

arXiv2024

The Sample-Communication Complexity Trade-off in Federated Q-Learning

We consider the problem of federated Q-learning, where $M$ agents aim to collaboratively learn the optimal Q-function of an unknown infinite-horizon Markov decision process with finite state and action spaces. We investigate the trade-off between sample and communication complexities for the widely used class of intermittent communication algorithms. We first establish the converse result, where it is shown that a federated Q-learning algorithm that offers any speedup with respect to the number of agents in the per-agent sample complexity needs to incur a communication cost of at least an order of $\frac{1}{1-\gamma}$ up to logarithmic factors, where $\gamma$ is the discount factor. We also propose a new algorithm, called Fed-DVR-Q, which is the first federated Q-learning algorithm to simultaneously achieve order-optimal sample and communication complexities. Thus, together these results provide a complete characterization of the sample-communication complexity trade-off in federated Q-learning.

cs.LG↗

arXiv2024

Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness

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 at the query points. Agents can share information through a central server, with the objective of minimizing regret that is accumulating over time $T$ and aggregating over agents. We develop the first algorithm that achieves the optimal regret order (as defined by centralized learning) with a communication cost that is sublinear in both $N$ and $T$. The key features of the proposed algorithm are the uniform exploration at the local agents and shared randomness with the central server. Working together with the sparse approximation of the GP model, these two key components make it possible to preserve the learning rate of the centralized setting at a diminishing rate of communication.

cs.LG↗

arXiv2024

Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency

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 random exploration approach achieves the optimal error rates. Our analysis is based on novel concentration bounds in an infinite dimensional Hilbert space established in this work, which may be of independent interest. We further develop an algorithm based on random exploration with domain shrinking and establish its order-optimal regret guarantees under both noise-free and noisy settings. In the noise-free setting, our analysis closes the existing gap in regret performance and thereby resolves a COLT open problem. The proposed algorithm also enjoys a computational advantage over prevailing methods due to the random exploration that obviates the expensive optimization of a non-convex acquisition function for choosing the query points at each iteration.

cs.LG↗

arXiv2023

A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret

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 low communication cost measured in the total number of bits transmitted over the entire learning horizon. This is in contrast to existing studies which focus on the offline measure of simple regret for learning efficiency. The holistic measure for communication cost also departs from the prevailing approach that \emph{separately} tackles the communication frequency and the number of bits in each communication round.

cs.LG↗

arXiv2023

Collaborative Learning in Kernel-based Bandits for Distributed Users

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 client has direct access to random bandit feedback on its local objective, but only has a partial view of the global objective and relies on information exchange with other clients for collaborative learning. We adopt the kernel-based bandit framework where the objective functions belong to a reproducing kernel Hilbert space. We propose an algorithm based on surrogate Gaussian process (GP) models and establish its order-optimal regret performance (up to polylogarithmic factors). We also show that the sparse approximations of the GP models can be employed to reduce the communication overhead across clients.

stat.ML↗

arXiv2022

Distributed Linear Bandits under Communication Constraints

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 communications are carried over channels with fixed capacity, which limits the amount of information that can be transmitted in each use of the channels. We investigate the regret-communication trade-off by (i) establishing information-theoretic lower bounds on the required communications (in terms of bits) for achieving a sublinear regret order; (ii) developing an efficient algorithm that achieves the minimum sublinear regret order offered by centralized learning using the minimum order of communications dictated by the information-theoretic lower bounds. For sparse linear bandits, we show a variant of the proposed algorithm offers better regret-communication trade-off by leveraging the sparsity of the problem.

cs.LG↗

arXiv2022

Provably and Practically Efficient Neural Contextual Bandits

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-asymptotic error bounds on the difference between an overparameterized neural net and its corresponding neural tangent kernel, (ii) we propose an algorithm with a provably sublinear regret bound that is also efficient in the finite regime as demonstrated by empirical studies. The non-asymptotic error bounds may be of broader interest as a tool to establish the relation between the smoothness of the activation functions in neural contextual bandits and the smoothness of the kernels in kernel bandits.

stat.ML↗

arXiv2021

A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance

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 the first GP-based algorithm with an order-optimal regret guarantee. The proposed algorithm is rooted in the methodology of domain shrinking realized through a sequence of tree-based region pruning and refining to concentrate queries in increasingly smaller high-performing regions of the function domain. The search for high-performing regions is localized and guided by an iterative estimation of the optimal function value to ensure both learning efficiency and computational efficiency. Compared with the prevailing GP-UCB family of algorithms, the proposed algorithm reduces computational complexity by a factor of $O(T^{2d-1})$ (where $T$ is the time horizon and $d$ the dimension of the function domain).

stat.ML↗

arXiv2021

As Easy as ABC: Adaptive Binning Coincidence Test for Uniformity Testing

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 $\ell_1$ distance from the uniform distribution. We propose a sequential test that adapts to the unknown distribution under the alternative hypothesis. Referred to as the Adaptive Binning Coincidence (ABC) test, the proposed strategy adapts in two ways. First, it partitions the set of alternative distributions into layers based on their distances to the uniform distribution. It then sequentially eliminates the alternative distributions layer by layer in decreasing distance to the uniform, and subsequently takes advantage of favorable situations of a distant alternative by exiting early. Second, it adapts, across layers of the alternative distributions, the resolution level of the discretization for computing the coincidence statistic. The farther away the layer is from the uniform, the coarser the discretization is needed for eliminating/exiting this layer. It thus exits both early in the detection process and quickly by using a lower resolution to take advantage of favorable alternative distributions. The ABC test builds on a novel sequential coincidence test for discrete distributions, which is of independent interest. We establish the sample complexity of the proposed tests as well as a lower bound.

math.ST↗

arXiv2020

Disagreement-based Active Learning in Online Settings

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 examples. The objective is to minimize the number of queries while constraining the number of prediction errors over a horizon of length $T$. We develop a disagreement-based online learning algorithm for a general hypothesis space and under the Tsybakov noise. We show that the proposed algorithm has a label complexity of $O(dT^{\frac{2-2α}{2-α}}\log^2 T)$ under a constraint of bounded regret in terms of classification errors, where $d$ is the VC dimension of the hypothesis space and $α$ is the Tsybakov noise parameter. We further establish a matching (up to a poly-logarithmic factor) lower bound, demonstrating the order optimality of the proposed algorithm. We address the tradeoff between label complexity and regret and show that the algorithm can be modified to operate at a different point on the tradeoff curve.

cs.LG↗

arXiv2020

Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization

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 the proposed optimization algorithm is an optimal control of the minimization precision in each iteration. We establish the optimal precision control and the resulting order-optimal regret performance for strongly convex and separably nonsmooth functions. An interesting finding is that the optimal progression of precision across iterations is independent of the low-dimensional CM routine employed, suggesting a general framework for extending low-dimensional optimization routines to high-dimensional problems. The proposed algorithm is amenable to online implementation and inherits the scalability and parallelizability properties of CM for large-scale optimization. Requiring only a sublinear order of message exchanges, it also lends itself well to distributed computing as compared with the alternative approach of coordinate gradient descent.

stat.ML↗

arXiv2020

Stochastic Gradient Descent on a Tree: an Adaptive and Robust Approach to Stochastic Convex Optimization

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 the distribution of the random gradients, a learning algorithm sequentially chooses query points with the objective of minimizing regret defined as the expected cumulative loss of the function values at the query points in excess to the minimum value of the function. An approach based on devising a biased random walk on an infinite-depth binary tree constructed through successive partitioning of the domain of the function is developed. Each move of the random walk is guided by a sequential test based on confidence bounds on the empirical mean constructed using the law of the iterated logarithm. With no tuning parameters, this learning algorithm is robust to heavy-tailed noise with infinite variance and adaptive to unknown function characteristics (specifically, convex, strongly convex, and nonsmooth). It achieves the corresponding optimal regret orders (up to a $\sqrt{\log T}$ or a $\log\log T$ factor) in each class of functions and offers better or matching regret orders than the classical stochastic gradient descent approach which requires the knowledge of the function characteristics for tuning the sequence of step-sizes.

stat.ML↗

arXiv2017

Spatial Field estimation from Samples taken at Unknown Locations generated by an Unknown Autoregressive Process

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 sensing stations and has nominal operational costs. In a mobile sensing setup, the accurate knowledge of sampling locations may lead to a manifold increase in the costs. Moreover, the inertia of the moving vehicle constrains the independence between the intersample distances, making them correlated. This work, thus, aims at estimating spatially bandlimited fields from samples, corrupted with measurement noise, collected on sampling locations obtained from an autoregressive model on the intersample distances. The autoregressive model is used to capture the correlation between the intersample distances. In this setup of sampling at unknown sampling locations obtained from an autoregressive model on intersample distances, the mean squared error between the field and its estimated version has been shown to decrease as O($1/n$), where $n$ is the average number of samples taken by the moving sensor.

cs.IT↗

arXiv2017

On Bandlimited Spatiotemporal Field Sampling with Location and Time Unaware Mobile Sensors

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 and location-unaware sensing of spatial fields. In this work, the general class of fields governed by a constant coefficient linear partial differential equations is considered. This class models many physical fields including temperature, pollution, and diffusion fields. The analysis is presented in one dimension for a first exposition. It is assumed that a mobile sensing unit is available to sample the spatiotemporal field of interest at unknown locations and unknown times -- both generated by independent and unknown renewal processes. Based on measurement-noise affected samples, a spatial field reconstruction algorithm is proposed. It is shown that if the initial condition on the field is bandlimited, then the mean squared error between the original and the estimated field decreases as $O(1/n)$, where $n$ is the average sampling density of the mobile sensor. The field reconstruction algorithm is universal, that is, it does not require the knowledge of unknown sampling locations' or unknown time instants' statistical distributions.

cs.IT↗