Anish Acharya

Anish Acharya

Auto-generated profile, based on publicly available information

Anish Acharya

ECE Department, The University of Texas at Austin, Austin, TX, USA

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 December 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
AHAbolfazl Hashemi
Abolfazl Hashemi
AAAnish Acharya
Anish Acharya
RDRudrajit Das
Rudrajit Das
HVHaris Vikalo
Haris Vikalo
SSSujay Sanghavi
Sujay Sanghavi
IDInderjit S. Dhillon
Inderjit S. Dhillon
Federated learning (FL) is an emerging collaborative machine learning (ML) framework that enables training of predictive models in a distributed fashion where the communication among the participating nodes are facilitated by a central server. To deal with the communication bottleneck at the server, decentralized FL (DFL) methods advocate rely on local communication of nodes with their neighbors according to a specific communication network. In DFL, it is common algorithmic practice to have nodes interleave (local) gradient descent iterations with gossip (i.e., averaging over the network) steps. As the size of the ML models grows, the limited communication bandwidth among the nodes does not permit communication of full-precision messages; hence, it is becoming increasingly common to require that messages be lossy, compressed versions of the local parameters. The requirement of communicating compressed messages gives rise to the important question: given a fixed communication budget, what should be our communication strategy to minimize the (training) loss as much as possible? In this article, we explore this direction, and show that in such compressed DFL settings, there are benefits to having multiple gossip steps between subsequent gradient iterations, even when the cost of doing so is appropriately accounted for, e.g., by means of reducing the precision of compressed information. In particular, we show that having ${\mathcal O}(\log \frac{1}{\epsilon })$ gradient iterations with constant step size - and ${\mathcal O}(\log \frac{1}{\epsilon })$ gossip steps between every pair of these iterations - enables convergence to within $\epsilon$ of the optimal value for a class of non-convex problems that arise in the training of deep learning models, namely, smooth non-convex objectives satisfying Polyak-Łojasiewicz condition. Empirically, we show that our proposed scheme bridges the gap between centralized gradient descent and DFL on various machine learning tasks across different network topologies and compression operators.

14 June 2024 in IEEE Journal on Selected Areas in Information Theory
Verified
Journal Article
Closed access
JWJay Whang
Jay Whang
ANAlliot Nagle
Alliot Nagle
AAAnish Acharya
Anish Acharya
HKHyeji Kim
Hyeji Kim
ADAlexandros G. Dimakis
Alexandros G. Dimakis
We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. This seminal result was later extended to lossy compression of distributed sources by Wyner, Ziv, Berger, and Tung. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. Here we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational auto-encoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR. Our code is made available at https://github.com/acnagle/neural-dsc.

1 June 2009
Verified
Conference Paper
Closed access
MGM. Ghosh
M. Ghosh
ACA. Chakraborty
A. Chakraborty
AAA. Acharya
A. Acharya
AKAmit Konar
Amit Konar
BPB. K. Panigrahi
B. K. Panigrahi
The paper provides a novel approach to represent cooperative/competitive interactions among coexisting emotions by a recurrent neural dynamics, and proposes a scheme for parameter estimation of the dynamics from the facial expressions of the subjects, psychologically excited by audio-visual stimulus taken from select commercial movies. Conditions for chaotic and stable behavior of the neural dynamics have been derived, and the same parametric conditions are used to predict the fluctuating dynamic behavior of emotions by testing the satisfiability of the conditions over the measured range of parameters.

17 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
JWJay Whang
Jay Whang
ANAlliot Nagle
Alliot Nagle
AAAnish Acharya
Anish Acharya
HKHyeji Kim
Hyeji Kim
ADAlexandros G. Dimakis
Alexandros G. Dimakis
Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. Here we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational Autoencoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR.