no code implementations • 16 Jul 2023 • Heng Zhu, Avishek Ghosh, Arya Mazumdar
We approach this problem in a worst-case scenario, without any prior information on the vector, but allowing for the use of randomized compression maps.
1 code implementation • 20 Oct 2022 • Harshvardhan, Avishek Ghosh, Arya Mazumdar
\texttt{SR-FCA} treats each user as a singleton cluster as an initialization, and then successively refine the cluster estimation via exploiting similar users belonging to the same cluster.
no code implementations • 23 Jul 2022 • Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
Furthermore, while the previous result is shown to hold only in the asymptotic regime (as $n \to \infty$), our result for these "locally rich" action spaces is any-time.
no code implementations • 6 Jul 2022 • Avishek Ghosh, Sayak Ray Chowdhury
We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approximations.
no code implementations • 31 May 2022 • Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran, Tara Javidi, Arya Mazumdar
We propose and analyze a decentralized and asynchronous learning algorithm, namely Decentralized Non-stationary Competing Bandits (\texttt{DNCB}), where the agents play (restrictive) successive elimination type learning algorithms to learn their preference over the arms.
no code implementations • 26 May 2022 • Avishek Ghosh, Arya Mazumdar, Soumyabrata Pal, Rajat Sen
In this paper we show that a version of the popular alternating minimization (AM) algorithm finds the best fit lines in a dataset even when a realizable model is not assumed, under some regularity conditions on the dataset and the initial points, and thereby provides a solution for the ERM.
no code implementations • 19 May 2022 • Avishek Ghosh, Abishek Sankararaman
The (poly) logarithmic regret of \texttt{LR-SCB} stems from two crucial facts: (a) the application of a norm adaptive algorithm to exploit the parameter estimation and (b) an analysis of the shifted linear contextual bandit algorithm, showing that shifting results in increasing regret.
no code implementations • 13 Jul 2021 • Avishek Ghosh, Sayak Ray Chowdhury, Kannan Ramchandran
We propose and analyze a novel algorithm, namely \emph{Adaptive Reinforcement Learning (General)} (\texttt{ARL-GEN}) that adapts to the smallest such family where the true transition kernel $P^*$ lies.
no code implementations • 7 Jul 2021 • Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We consider the problem of model selection for the general stochastic contextual bandits under the realizability assumption.
no code implementations • 15 Jun 2021 • Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We show that, for any agent, the regret scales as $\mathcal{O}(\sqrt{T/N})$, if the agent is in a `well separated' cluster, or scales as $\mathcal{O}(T^{\frac{1}{2} + \varepsilon}/(N)^{\frac{1}{2} -\varepsilon})$ if its cluster is not well separated, where $\varepsilon$ is positive and arbitrarily close to $0$.
no code implementations • 16 May 2021 • Vipul Gupta, Avishek Ghosh, Michal Derezinski, Rajiv Khanna, Kannan Ramchandran, Michael Mahoney
To enhance practicability, we devise an adaptive scheme to choose L, and we show that this reduces the number of local iterations in worker machines between two model synchronizations as the training proceeds, successively refining the model quality at the master.
no code implementations • 17 Mar 2021 • Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar, Kannan Ramchandran
Moreover, we validate our theoretical findings with experiments using standard datasets and several types of Byzantine attacks, and obtain an improvement of $25\%$ with respect to first order methods in iteration complexity.
no code implementations • NeurIPS 2020 • Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar
We develop a distributed second order optimization algorithm that is communication-efficient as well as robust against Byzantine failures of the worker machines.
3 code implementations • NeurIPS 2020 • Avishek Ghosh, Jichan Chung, Dong Yin, Kannan Ramchandran
We address the problem of federated learning (FL) where users are distributed and partitioned into clusters.
no code implementations • 4 Jun 2020 • Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
This is the first algorithm that achieves such model selection guarantees.
no code implementations • 23 Apr 2020 • Avishek Ghosh, Kannan Ramchandran
Furthermore, we compare AM with a gradient based heuristic algorithm empirically and show that AM dominates in iteration complexity as well as wall-clock time.
no code implementations • 21 Nov 2019 • Avishek Ghosh, Raj Kumar Maity, Swanand Kadhe, Arya Mazumdar, Kannan Ramchandran
Moreover, we analyze the compressed gradient descent algorithm with error feedback (proposed in \cite{errorfeed}) in a distributed setting and in the presence of Byzantine worker machines.
no code implementations • 21 Jun 2019 • Avishek Ghosh, Ashwin Pananjady, Adityanand Guntuboyina, Kannan Ramchandran
Max-affine regression refers to a model where the unknown regression function is modeled as a maximum of $k$ unknown affine functions for a fixed $k \geq 1$.
no code implementations • 16 Jun 2019 • Avishek Ghosh, Justin Hong, Dong Yin, Kannan Ramchandran
Then, leveraging the statistical model, we solve the robust heterogeneous Federated Learning problem \emph{optimally}; in particular our algorithm matches the lower bound on the estimation error in dimension and the number of data points.
no code implementations • 9 Jul 2018 • Avishek Ghosh, Kannan Ramchandran
We argue that the error in the score estimate accumulated over $T$ iterations is small if the regret of the online convex game is small.
no code implementations • 23 Apr 2017 • Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
Regret guarantees for state-of-the-art linear bandit algorithms such as Optimism in the Face of Uncertainty Linear bandit (OFUL) hold under the assumption that the arms expected rewards are perfectly linear in their features.