Anish Acharya

Senior Research Scientist
Amazon Web Services
Austin, Texas

About

I am a Senior Research Scientist at Amazon Web Services in Austin, Texas, where I work on recursive self-improvement loops for multi-agent swarms. I received my PhD in Electrical and Computer Engineering from The University of Texas at Austin in 2025, advised by Inderjit S. Dhillon and Sujay Sanghavi, with a thesis on Robust and Efficient Learning in High Dimensions from Noisy Data.

During my PhD I was a research scientist at Meta (Capacity Engineering and FAIR) and Microsoft (Speech and Dialog Research), and led AI research at Eidon AI. Before it, I spent three years at Amazon building NLP models for Alexa, moving from software engineering to applied science across Alexa ML, Alexa AI, and AGI.

Earlier roles include data science at eBay and Schlumberger and a visiting research position at the Toyota Technological Institute at Chicago with David McAllester. I hold an MS in EECS from UC Irvine and a BE from Jadavpur University.

Research

I am broadly interested in learning theory. My research studies learning as a feedback process under imperfect information. A learning system observes noisy or incomplete feedback, constructs a reward or target, updates its weights, policies, prompts, tools, or coordination structure under constraints, validates the resulting behavior, and changes the observations available in the next round.

Across these threads, I ask what is identifiable from imperfect feedback, how an optimization objective should be constructed when true utility is unobserved, which updates are computationally feasible, and when repeated adaptation is dynamically stable. My current research brings these questions together in models and agent systems that evaluate and modify their own behavior.

Publications

Papers

2026

conferenceSPLICE: Structured Prompt Local Iterative Combinatorial Evolution

Anish Acharya, P Studans, A Dhanda, N V Rao, V A Khatri, S A Niaki, B Verkhovsky

Conference on Neural Information Processing Systems (NeurIPS), 2026
workshopRoPoLL: Robust Panel of LLM Judges

Anish Acharya, K Pan, B Verkhovsky

International Conference on Machine Learning (ICML), 2026 · AgenticUQ Workshop

OpenReview arXiv Amazon Science
workshopOrchOpt: Validation-Gated Architecture Search for Self-Organizing Multi-Agent Orchestration

A Dhanda, S A Niaki, Anish Acharya, B Verkhovsky

Conference on Language Modeling (COLM), 2026 · Lifelong Agents Workshop

OpenReview Amazon Science

2025

conferenceGeometric Median Matching for Robust k-Subset Selection from Noisy Data

Anish Acharya, S Sanghavi, A G Dimakis, I S Dhillon

International Conference on Machine Learning (ICML), 2025

PMLR OpenReview arXiv

Short version: ICML 2024 FMWild Workshop

2024

journalNeural Distributed Source Coding

A Nagle, J Whang, Anish Acharya, H Kim, A Dimakis

IEEE Journal on Selected Areas in Information Theory (IEEE JSAIT), 2024

IEEE Xplore arXiv

2022

conferenceFaster Non-Convex Federated Learning via Global and Local Momentum

R Das, Anish Acharya, A Hashemi, S Sanghavi, I Dhillon, U Topcu

Conference on Uncertainty in Artificial Intelligence (UAI), 2022 · Spotlight

OpenReview arXiv
conferenceRobust Training in High Dimensions via Block Coordinate Geometric Median Descent

Anish Acharya, A Hashemi, P Jain, S Sanghavi, I Dhillon, U Topcu

International Conference on Artificial Intelligence and Statistics (AISTATS), 2022 · Spotlight

PMLR Code Poster Slides

Short version: Joint IFML/CCSI Symposium (Simons Institute, UC Berkeley) · Short version: NSF-TRIPODS Workshop on Communication Efficient Distributed Optimization
workshopPositive Unlabeled Contrastive Learning

Anish Acharya, S Sanghavi, L Jing, B Bhushanam, D Choudhary, M Rabbat, I Dhillon

International Conference on Machine Learning (ICML), 2022 · PODS Workshop

Proceedings arXiv

Extended version: Understanding Contrastive Representation Learning from Positive Unlabeled (PU) Data — arXiv:2402.06038 · Short version: Simons Institute, UC Berkeley — Data-Driven Decision Processes Workshop
workshopLDKP: A Dataset for Identifying Keyphrases from Long Scientific Documents

D Mahata, N Agarwal, D Gautam, A Kumar, S Parekh, Y K Singla, Anish Acharya, R R Shah

ACM International Conference on Information and Knowledge Management (CIKM), 2022 · DL4SR Workshop

CEUR-WS arXiv HF Dataset

2021

journalOn the Benefits of Multiple Gossip Steps in Communication Constrained Federated Learning

A Hashemi, Anish Acharya, R Das, H Vikalo, S Sanghavi, I Dhillon

IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS), 2021

IEEE Xplore Code arXiv
conferenceAlexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems

Anish Acharya, S Adhikari, S Agarwal, V Auvray, N Belgamwar, A Biswas, S Chandra, T Chung, M Zarandi, R Gabriel, S Gao, R Goel, D Hakkani-Tur, J Jezabek, A Jha, J Kao, P Krishnan, P Ku, A Goyal, C Lin, Q Liu, A Mandal, A Metallinou, V Naik, Y Pan, S Paul, V Perera, A Sethi, M Shen, N Strom, E Wang

Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021 · Demonstrations Track

ACL Anthology Skill
conferenceGupShup: An Annotated Corpus for Abstractive Summarization of Open-Domain Code-Switched Conversations

L Mehnaz, D Mahata, A Kumar, U S Gunturi, R Jain, G Gupta, R Gosangi, I G Lee, Anish Acharya, R Shah

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021

ACL Anthology Code

2019

conferenceOnline Embedding Compression for Text Classification using Low Rank Matrix Factorization

Anish Acharya, R Goel, A Metallinou, I Dhillon

AAAI Conference on Artificial Intelligence (AAAI), 2019 · Spotlight

Proceedings Code arXiv

2014

journalExtending The Concept of Analog Butterworth Filter For Fractional Domain

Anish Acharya, S Das, I Pan, S Das

Signal Processing (Elsevier), 2014

ScienceDirect arXiv
journalSimulation studies on the design of optimum PID controllers to suppress chaotic oscillations in a family of Lorenz-like multi-wing attractors

S Das, Anish Acharya, I Pan

Mathematics and Computers in Simulation (Elsevier), 2014

ScienceDirect arXiv

2013

conferenceStability Analysis Of Delayed System Using Bode's Integral

Anish Acharya, D Mitra, K Halder

International Conference on Computer Communication and Informatics (ICCCI), 2013

IEEE Xplore arXiv

2012

conferenceOptimum PID Control of Multi-wing Attractors in A Family of Lorenz-like Chaotic Systems

Anish Acharya, S Das, I Pan

International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2012

IEEE Xplore arXiv
conferenceOptimized Quality Factor of Fractional Order Analog Filters with Band-Pass and Band-Stop Characteristics

A Pakhira, S Das, Anish Acharya, I Pan, S Saha

International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2012

IEEE Xplore arXiv
conferenceIdentification of nonlinear systems from the knowledge around different operating conditions: a feed-forward multilayer Artificial Neural Net (ANN) based approach

S Saha, S Das, Anish Acharya, A Kumar, S Mukherjee, I Pan, A Gupta

International Conference on Parallel, Distributed and Grid Computing (PDGC), 2012

IEEE Xplore

2011

conferenceLeast square and instrumental variable system identification of AC servo position control system with fractional Gaussian noise

S Das, A Kumar, I Pan, Anish Acharya, S Das, A Gupta

International Conference on Energy, Automation and Signal (ICEAS), 2011

IEEE Xplore

Granted US patents

2022-07

Goal Oriented Dialog Generation using Dialog Template, API and Entity data

Anish Acharya, A Metallinou, T Chung, S Paul, S Chandra, C Lin, D H Tur, A Mandal

US11393454 · Amazon · USPTO
2020-12

Natural Language Processing

Compressing word embeddings with low-rank matrix factorization for on-device natural language understanding.

Anish Acharya, A Metallinou, R Goel, I Dhillon

US10872601 · Amazon · USPTO

Thesis

Robust and Efficient Learning in High Dimensions from Noisy Data

PhD, Electrical and Computer Engineering · The University of Texas at Austin, 2025
Advised by Inderjit S. Dhillon and Sujay Sanghavi. Committee: Alex Dimakis, Ludwig Schmidt, Nhat Ho.

Experience

Research experience

Amazon · Austin, TX · Spring 2025 –
- Senior Research Scientist, AWS
University of Texas at Austin · Austin, TX · Fall 2019 – Spring 2025
- Graduate Research Assistant, ECE and CS
Eidon AI · Austin, TX · Summer 2024 – Winter 2025
- Head of AI Research
Meta · Menlo Park, CA · Summer 2021 – Fall 2022
- Student ResearcherFall 2022
- Research ScientistSummer 2022
- Student ResearcherFall 2021
- Research ScientistSummer 2021
Hosted by Li Jing, Bhargav Bhushanam, Dhruv Choudhary, Michael Rabbat
Microsoft · Redmond, WA · Summer 2020
- Research Scientist
Hosted by Kenichi Kumatani, Dimitrios Dimitriadis
Amazon · Sunnyvale, CA · Summer 2016 – Spring 2019
- Applied Scientist, AGISummer 2018 – Spring 2019
- Applied Scientist, Alexa AISpring 2018 – Summer 2018
- Applied Scientist, Alexa MLWinter 2017 – Spring 2018
- Software Development Engineer, Amazon DevicesSummer 2016 – Winter 2017
eBay · San Jose, CA · Fall 2015 – Summer 2016
- Data Scientist, Customer Insights and Analytics
Schlumberger · Houston, TX · Spring 2015 – Fall 2015
- Data Scientist
FEM Inc. · Los Angeles, CA · Winter 2015
- Data Engineer
Toyota Technological Institute Chicago · Chicago, IL · Summer 2014
- Visiting Research Assistant
Hosted by David McAllester

Education

PhD, Electrical and Computer Engineering

The University of Texas at Austin · Austin, TX · Fall 2019 – Spring 2025

Thesis: Robust and Efficient Learning in High Dimensions from Noisy Data

Advised by Inderjit S. Dhillon and Sujay Sanghavi

Committee: Alex Dimakis, Ludwig Schmidt, Nhat Ho
MS, Electrical Engineering and Computer Science

University of California, Irvine · Irvine, CA · Fall 2013 – Fall 2014
BE, Electronics and Instrumentation Engineering

Jadavpur University · Kolkata, India · Spring 2009 – Spring 2013

Teaching

Amazon Web Services · Austin, TX · Winter 2026 –
- Instructor, Embedding AI into Products: Evaluation-Driven DevelopmentAWS GenAI Training
  Summer 2026
- Instructor, Embedding AI into Products: Governance and GuardrailsAWS GenAI Training
  Spring 2026
University of Texas at Austin · Austin, TX · Fall 2023 – Fall 2025
- Instructor, Directed Reading Program: Natural Language Optimization
  Fall 2025
- Teaching Assistant, MIS 285N: Introduction to Deep Learning
  Spring 2024
- Teaching Assistant, MIS 185N: Emerging Trends in Machine Learning
  Spring 2024
- Teaching Assistant, ECE 461P: Data Science Principles
  Fall 2023
University of California Irvine · Irvine, CA · Fall 2013 – Fall 2014
- Teaching Assistant, EECS 50: Discrete Time Signals and Systems
  Fall 2014
- Teaching Assistant, EECS 280A: Advanced Engineering Electromagnetics
  Spring 2014
- Teaching Assistant, EECS 118: Knowledge Management and Software Eng.
  Winter 2014
- Teaching Assistant, EECS 119: Introduction to VLSI
  Fall 2013

Academic Service

Reviewer, Conferences
- International Conference on Machine Learning (ICML)
- Conference on Neural Information Processing Systems (NeurIPS)
- International Conference on Learning Representations (ICLR)
- International Conference on Artificial Intelligence and Statistics (AISTATS)
- Conference on Uncertainty in Artificial Intelligence (UAI)
- Annual Meeting of the Association for Computational Linguistics (ACL)
- IEEE International Symposium on Information Theory (ISIT)
Reviewer, Journals
- Journal of Machine Learning Research (MIT Press)
- Transactions on Knowledge and Data Engineering (IEEE)
- Pattern Recognition Letters (Elsevier)
- Cognitive Neurodynamics (Springer Nature)
- Discover Electronics (Springer Nature)
Program Committee
- International Conference on Machine Learning (ICML)
- AAAI Conference on Artificial Intelligence (AAAI)