Search Results for author: Ketan Rajawat

Found 22 papers, 4 papers with code

Optimized Gradient Tracking for Decentralized Online Learning

1 code implementation10 Jun 2023 Shivangi Dubey Sharma, Ketan Rajawat

This work considers the problem of decentralized online learning, where the goal is to track the optimum of the sum of time-varying functions, distributed across several nodes in a network.

Sharpened Lazy Incremental Quasi-Newton Method

1 code implementation26 May 2023 Aakash Lahoti, Spandan Senapati, Ketan Rajawat, Alec Koppel

Specifically, they exhibit a superlinear rate with $O(d^2)$ cost in contrast to the linear rate of first-order methods with $O(d)$ cost and the quadratic rate of second-order methods with $O(d^3)$ cost.

Second-order methods

Low-complexity subspace-descent over symmetric positive definite manifold

1 code implementation3 May 2023 Yogesh Darmwal, Ketan Rajawat

This work puts forth low-complexity Riemannian subspace descent algorithms for the minimization of functions over the symmetric positive definite (SPD) manifold.

Riemannian optimization

Variational Bayesian Filtering with Subspace Information for Extreme Spatio-Temporal Matrix Completion

no code implementations20 Jan 2022 Charul Paliwal, Pravesh Biyani, Ketan Rajawat

We evaluate the proposed Variational Bayesian Filtering with Subspace Information (VBFSI) method to impute matrices in real-world traffic and air pollution data.

Imputation Low-Rank Matrix Completion

Projection-Free Algorithm for Stochastic Bi-level Optimization

no code implementations22 Oct 2021 Zeeshan Akhtar, Amrit Singh Bedi, Srujan Teja Thomdapu, Ketan Rajawat

The proposed $\textbf{S}$tochastic $\textbf{C}$ompositional $\textbf{F}$rank-$\textbf{W}$olfe ($\textbf{SCFW}$) is shown to achieve a sample complexity of $\mathcal{O}(\epsilon^{-2})$ for convex objectives and $\mathcal{O}(\epsilon^{-3})$ for non-convex objectives, at par with the state-of-the-art sample complexities for projection-free algorithms solving single-level problems.

Denoising Matrix Completion +1

Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained Optimization

no code implementations14 Jul 2021 Zeeshan Akhtar, Ketan Rajawat

This paper considers stochastic convex optimization problems with two sets of constraints: (a) deterministic constraints on the domain of the optimization variable, which are difficult to project onto; and (b) deterministic or stochastic constraints that admit efficient projection.

STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning

no code implementations NeurIPS 2021 Prashant Khanduri, Pranay Sharma, Haibo Yang, Mingyi Hong, Jia Liu, Ketan Rajawat, Pramod K. Varshney

Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local update frequency, so that the WNs use the minimum number of samples and communication rounds to achieve the desired solution.

Federated Learning

Stochastic Compositional Gradient Descent under Compositional Constraints

no code implementations17 Dec 2020 Srujan Teja Thomdapu, Harshvardhan, Ketan Rajawat

Of particular interest is the large-scale setting where an oracle provides the stochastic gradients of the constituent functions, and the goal is to solve the problem with a minimal number of calls to the oracle.

General Classification regression +1

Distributed Optimisation With Communication Delays

no code implementations26 Nov 2020 Shuubham Ojha, Ketan Rajawat

In this paper we introduce a co-operative control strategy which makes convergence to optimum robust to communication delays.

Distributed Optimization Optimization and Control Systems and Control Systems and Control

Sparse Representations of Positive Functions via First and Second-Order Pseudo-Mirror Descent

no code implementations13 Nov 2020 Abhishek Chakraborty, Ketan Rajawat, Alec Koppel

We consider expected risk minimization problems when the range of the estimator is required to be nonnegative, motivated by the settings of maximum likelihood estimation (MLE) and trajectory optimization.

Practical Precoding via Asynchronous Stochastic Successive Convex Approximation

no code implementations3 Oct 2020 Basil M. Idrees, Javed Akhtar, Ketan Rajawat

In the online setting, where a single sample of the stochastic gradient of the loss is available at every iteration, the problem can be solved using the proximal stochastic gradient descent (SGD) algorithm and its variants.

Stochastic Optimization

Conservative Stochastic Optimization with Expectation Constraints

no code implementations13 Aug 2020 Zeeshan Akhtar, Amrit Singh Bedi, Ketan Rajawat

In this work, we propose the FW-CSOA algorithm that is not only projection-free but also achieves zero constraint violation with $\O\left(T^{-\frac{1}{4}}\right)$ decay of the optimality gap.

Matrix Completion Stochastic Optimization

Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction

no code implementations1 May 2020 Prashant Khanduri, Pranay Sharma, Swatantra Kafle, Saikiran Bulusu, Ketan Rajawat, Pramod K. Varshney

In this work, we propose a distributed algorithm for stochastic non-convex optimization.

Optimization and Control Distributed, Parallel, and Cluster Computing

Consistent Online Gaussian Process Regression Without the Sample Complexity Bottleneck

no code implementations23 Apr 2020 Alec Koppel, Hrusikesha Pradhan, Ketan Rajawat

Gaussian processes provide a framework for nonlinear nonparametric Bayesian inference widely applicable across science and engineering.

Bayesian Inference Gaussian Processes +1

Optimally Compressed Nonparametric Online Learning

no code implementations25 Sep 2019 Alec Koppel, Amrit Singh Bedi, Ketan Rajawat, Brian M. Sadler

Batch training of machine learning models based on neural networks is now well established, whereas to date streaming methods are largely based on linear models.

Adaptive Kernel Learning in Heterogeneous Networks

no code implementations1 Aug 2019 Hrusikesha Pradhan, Amrit Singh Bedi, Alec Koppel, Ketan Rajawat

We consider learning in decentralized heterogeneous networks: agents seek to minimize a convex functional that aggregates data across the network, while only having access to their local data streams.

Distributed Inexact Successive Convex Approximation ADMM: Analysis-Part I

no code implementations21 Jul 2019 Sandeep Kumar, Ketan Rajawat, Daniel P. Palomar

Different from a number of existing approaches, however, the proposed framework is flexible enough to incorporate a class of non-convex objective functions, allow distributed operation with and without a fusion center, and include variance reduced methods as special cases.

Online Learning over Dynamic Graphs via Distributed Proximal Gradient Algorithm

no code implementations16 May 2019 Rishabh Dixit, Amrit Singh Bedi, Ketan Rajawat

The empirical performance of the proposed algorithm is tested on the distributed dynamic sparse recovery problem, where it is shown to incur a dynamic regret that is close to that of the centralized algorithm.

Stochastic Multidimensional Scaling

no code implementations21 Dec 2016 Ketan Rajawat, Sandeep Kumar

Multidimensional scaling (MDS) is a popular dimensionality reduction techniques that has been widely used for network visualization and cooperative localization.

Dimensionality Reduction Stochastic Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.