Anish Acharya

Anish Acharya
University of Texas at Austin | UT · Department of Electrical & Computer Engineering

Doctor of Philosophy

About

28
Publications
7,674
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
166
Citations
Additional affiliations
June 2021 - December 2021
Meta
Position
  • Research Intern
June 2020 - August 2020
Microsoft
Position
  • Researcher
May 2016 - July 2019
Amazon
Position
  • Researcher
Education
July 2019 - November 2023
University of Texas at Austin
Field of study
  • Electrical Engineering and Computer Sciences
August 2013 - November 2014
University of California, Irvine
Field of study
  • Electrical Engineering and Computer Sciences
June 2009 - May 2013
Jadavpur University
Field of study
  • Instrumentation and Electronics Engineering

Publications

Publications (28)
Article
This paper proposes the design of Fractional Order (FO) Butterworth filter in complex w-plane (w=sq; q being any real number) considering the presence of under-damped, hyper-damped, ultra-damped poles. This is the first attempt to design such fractional Butterworth filters in complex w-plane instead of complex s-plane, as conventionally done for in...
Preprint
Full-text available
Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for every new domain, limiting scalability of such systems. Similarly, rule-based dialogue systems requi...
Preprint
Full-text available
Distributed source coding 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 that has no access to the correlated side information can asymptotically achieve the same compression rate as when the side information is availab...
Preprint
Full-text available
Geometric median (Gm) is a classical method in statistics for achieving a robust estimation of the uncorrupted data; under gross corruption, it achieves the optimal breakdown point of 0.5. However, its computational complexity makes it infeasible for robustifying stochastic gradient descent (SGD) for high-dimensional optimization problems. In this...
Preprint
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during t...
Preprint
Full-text available
Self-supervised pretraining on unlabeled data followed by supervised finetuning on labeled data is a popular paradigm for learning from limited labeled examples. In this paper, we investigate and extend this paradigm to the classical positive unlabeled (PU) setting - the weakly supervised task of learning a binary classifier only using a few labele...
Preprint
Full-text available
Identifying keyphrases (KPs) from text documents is a fundamental task in natural language processing and information retrieval. Vast majority of the benchmark datasets for this task are from the scientific domain containing only the document title and abstract information. This limits keyphrase extraction (KPE) and keyphrase generation (KPG) algor...
Article
Full-text available
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 l...
Preprint
Full-text available
In this paper we study test time decoding; an ubiquitous step in almost all sequential text generation task spanning across a wide array of natural language processing (NLP) problems. Our main contribution is to develop a continuous relaxation framework for the combinatorial NP-hard decoding problem and propose Disco - an efficient algorithm based...
Preprint
Full-text available
Code-switching is the communication phenomenon where speakers switch between different languages during a conversation. With the widespread adoption of conversational agents and chat platforms, code-switching has become an integral part of written conversations in many multi-lingual communities worldwide. This makes it essential to develop techniqu...
Preprint
Full-text available
In decentralized optimization, it is common algorithmic practice to have nodes interleave (local) gradient descent iterations with gossip (i.e. averaging over the network) steps. Motivated by the training of large-scale machine learning models, it is also increasingly common to require that messages be {\em lossy compressed} versions of the local p...
Conference Paper
Full-text available
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during t...
Preprint
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during t...
Article
Full-text available
Estimates of image gradients play a ubiquitous role in image segmentation and classification problems since gradients directly relate to the boundaries or the edges of a scene. This paper proposes an unified approach to gradient estimation based on fractional calculus that is computationally cheap and readily applicable to any existing algorithm th...
Article
Full-text available
At this moment Autonomous cars are probably the biggest and most talked about technology in the Robotics Research Community. In spite of great technological advances over past few years a full edged autonomous car is still far from reality. This article talks about the existing system and discusses the possibility of a Computer Vision enabled drivi...
Article
Full-text available
This paper is a review of the popular Benjamini Hochberg Method and other related useful methods of Multiple Hypothesis testing. This is written with the purpose of serving a short but complete easy to understand review of the main article with proper background. The paper titled 'Controlling the False Discovery Rate-a practical and powerful Approa...
Article
Full-text available
This article provides a step by step development of designing a Object Detection scheme using the HOG based Feature Pyramid aligned with the concept of Template Matching.
Article
Full-text available
Multi-wing chaotic attractors are highly complex nonlinear dynamical systems with higher number of index-2 equilibrium points. Due to the presence of several equilibrium points, randomness and hence the complexity of the state time series for these multi-wing chaotic systems is much higher than that of the conventional double-wing chaotic attractor...
Conference Paper
Full-text available
The PID controller parameters can be adjusted in such a manner that it gives the desired frequency response and the results are found using the Bodes integral formula in order to adjust the slope of the nyquist curve in a desired manner. The same idea is applied for plants with time delay . The same has also been done in a new approach . The delay...
Conference Paper
Full-text available
The paper investigates nonlinear system identification using system output data at various linearized operating points. A feed-forward multi-layer Artificial Neural Network (ANN) based approach is used for this purpose and tested for two target applications i.e. nuclear reactor power level monitoring and an AC servo position control system. Various...
Conference Paper
Full-text available
Multi-wing chaotic attractors are highly complex nonlinear dynamical systems with higher number of index-2 equilibrium points. Due to the presence of several equilibrium points, randomness of the state time series for these multi-wing chaotic systems is higher than that of the conventional double wing chaotic attractors. A real coded Genetic Algori...
Conference Paper
Full-text available
Fractional order (FO) filters have been investigated in this paper, with band-pass (BP) and band-stop (BS) characteristics, which can not be achieved with conventional integer order filters with orders lesser then two. The quality factors for symmetric and asymmetric magnitude response have been optimized using real coded Genetic Algorithm (GA) for...
Conference Paper
Full-text available
In this paper, the classical Least Square Estimator (LSE) and its improved version the Instrumental Variable (IV) estimator have been used for the identification of an ac servo motor position control system. The data for system identification has been collected from a practical test set-up for fixed command on the final angular position of the serv...

Network

Cited By