Work with Anit Kumar Sahu | NotedSource
Anit Kumar Sahu is a highly accomplished researcher and
engineer in the field of Electrical and Computer
Engineering. He earned his PhD from Carnegie Mellon
University in 2018, where he focused his research on
statistical machine learning. During his time at CMU, he
received the A.G. Jordan award for outstanding thesis.
After completing his PhD, Anit joined Amazon Services LLC
as a Senior Applied Scientist, where he works on
developing innovative solutions for complex business
problems using machine learning and artificial
intelligence. Prior to joining Amazon, Anit worked at
Bosch Center for Artificial Intelligence as a Machine
Learning Research Scientist, where he developed
cutting-edge algorithms for adversarial machine learning.
He is currently Principal AI Scientist at GE Healthcare
AI, where he is responsible for leading research and
development efforts in the healthcare sector. With his
extensive education and experience in both academia and
industry, Anit has become a leading expert in the field of
machine learning, computer vision, and artificial
intelligence. He has published numerous research papers in
top conferences and journals, and his work has been widely
cited by other researchers in the field. Apart from his
professional accomplishments, Anit is also passionate
about mentoring and teaching the next generation of
engineers and scientists. In his free time, Anit enjoys
hiking, trying new restaurants, and traveling to new
places. He also actively participates in various volunteer
activities and is dedicated to giving back to his
community.
https://cv.notedsource.io/me/47RXDDZJ
Anit Kumar Sahu
PhD from CMU working in ML/AI
Research Expertise
Federated Learning
Stochastic Optimization
Data Selection
Electrical and Electronic Engineering
Signal Processing
Applied Mathematics
Information Systems
Computer Networks and Communications
Library and Information Sciences
Computer Science Applications
Artificial Intelligence
Cognitive Neuroscience
Theoretical Computer Science
Software
Materials Chemistry
Electrochemistry
Energy Engineering and Power Technology
Control and Optimization
Mechanical Engineering
Mechanics of Materials
About
Anit Kumar Sahu is a highly accomplished
researcher and engineer in the field of
Electrical and Computer Engineering. He earned
his PhD from Carnegie Mellon University in
2018, where he focused his research on
statistical machine learning. During his time
at CMU, he received the A.G. Jordan award for
outstanding thesis. After completing his PhD,
Anit joined Amazon Services LLC as a Senior
Applied Scientist, where he works on
developing innovative solutions for complex
business problems using machine learning and
artificial intelligence. Prior to joining
Amazon, Anit worked at Bosch Center for
Artificial Intelligence as a Machine Learning
Research Scientist, where he developed
cutting-edge algorithms for adversarial
machine learning. He is currently Principal AI
Scientist at GE Healthcare AI, where he is
responsible for leading research and
development efforts in the healthcare sector.
With his extensive education and experience in
both academia and industry, Anit has become a
leading expert in the field of machine
learning, computer vision, and artificial
intelligence. He has published numerous
research papers in top conferences and
journals, and his work has been widely cited
by other researchers in the field. Apart from
his professional accomplishments, Anit is also
passionate about mentoring and teaching the
next generation of engineers and scientists.
In his free time, Anit enjoys hiking, trying
new restaurants, and traveling to new places.
He also actively participates in various
volunteer activities and is dedicated to
giving back to his community.
Legacy Map
Full ViewPublications
Federated Learning: Challenges, Methods,
and Future Directions
IEEE Signal Processing Magazine
2020
FedDANE: A Federated Newton-Type Method
2019 53rd Asilomar Conference on
Signals, Systems, and Computers
2019
MATCHA: Speeding Up Decentralized SGD via
Matching Decomposition Sampling
2019 Sixth Indian Control Conference
(ICC)
2019
Learning representations in Bayesian
Confidence Propagation neural networks
2020 International Joint Conference on
Neural Networks (IJCNN)
2020
Distributed stochastic optimization with
gradient tracking over strongly-connected
networks
2019 IEEE 58th Conference on Decision
and Control (CDC)
2019
Convergence Rates for Distributed
Stochastic Optimization Over Random
Networks
2018 IEEE Conference on Decision and
Control (CDC)
2018
Distributed Zeroth Order Optimization Over
Random Networks: A Kiefer-Wolfowitz
Stochastic Approximation Approach
2018 IEEE Conference on Decision and
Control (CDC)
2018
Distributed Constrained Recursive
Nonlinear Least-Squares Estimation:
Algorithms and Asymptotics
IEEE Transactions on Signal and
Information Processing over
Networks
2016
Federated Learning Challenges and
Opportunities: An Outlook
ICASSP 2022 - 2022 IEEE International
Conference on Acoustics, Speech and
Signal Processing (ICASSP)
2022
Simple and Efficient Hard Label Black-box
Adversarial Attacks in Low Query Budget
Regimes
Proceedings of the 27th ACM SIGKDD
Conference on Knowledge Discovery &
Data Mining
2021
About the social role of child and
adolescent psychiatrists in times of
epidemic
IACAPAP ArXiv
2020
Recursive Distributed Detection for
Composite Hypothesis Testing: Nonlinear
Observation Models in Additive Gaussian
Noise
IEEE Transactions on Information
Theory
2017
NON-ASYMPTOTIC RATES FOR COMMUNICATION
EFFICIENT DISTRIBUTED ZEROTH ORDER
STRONGLY CONVEX OPTIMIZATION
2018 IEEE Global Conference on Signal
and Information Processing
(GlobalSIP)
2018
$\mathcal {CIRFE}$: A Distributed Random
Fields Estimator
IEEE Transactions on Signal
Processing
2018
CREDO: A Communication-Efficient
Distributed Estimation Algorithm
2018 IEEE International Symposium on
Information Theory (ISIT)
2018
ActPerFL: Active Personalized Federated
Learning
Proceedings of the First Workshop on
Federated Learning for Natural Language
Processing (FL4NLP 2022)
2022
Decentralized Zeroth-Order Constrained
Stochastic Optimization Algorithms:
Frank–Wolfe and Variants With Applications
to Black-Box Adversarial Attacks
Proceedings of the IEEE
2020
Data-driven Thermal Model Inference with
ARMAX, in Smart Environments, based on
Normalized Mutual Information
2018 Annual American Control Conference
(ACC)
2018
Partial model averaging in Federated
Learning: Performance guarantees and
benefits
Neurocomputing
2023
Nonlinear Gradient Mappings and Stochastic
Optimization: A General Framework with
Applications to Heavy-Tail Noise
SIAM Journal on Optimization
2023
Matcha: A Matching-Based Link Scheduling
Strategy to Speed up Distributed
Optimization
IEEE Transactions on Signal
Processing
2022
Communication efficient distributed
weighted non-linear least squares
estimation
EURASIP Journal on Advances in Signal
Processing
2018
ILASR: Privacy-Preserving Incremental
Learning for Automatic Speech Recognition
at Production Scale
Proceedings of the 28th ACM SIGKDD
Conference on Knowledge Discovery and
Data Mining
2022
Dist-Hedge: A partial information setting
based distributed non-stochastic sequence
prediction algorithm
2017 IEEE Global Conference on Signal
and Information Processing
(GlobalSIP)
2017
Exploring the Error-Runtime Trade-off in
Decentralized Optimization
2020 54th Asilomar Conference on
Signals, Systems, and Computers
2020
Deep Active Learning with Noisy Oracle in
Object Detection
Proceedings of the 19th International
Joint Conference on Computer Vision,
Imaging and Computer Graphics Theory and
Applications
2024
Communication Efficient Distributed
Estimation Over Directed Random Graphs
IEEE EUROCON 2019 -18th International
Conference on Smart Technologies
2019
Field performance analysis of solar cell
designs
Journal of Power Sources Advances
2024
Federated Self-Learning with Weak
Supervision for Speech Recognition
ICASSP 2023 - 2023 IEEE International
Conference on Acoustics, Speech and
Signal Processing (ICASSP)
2023
Distributed empirical risk minimization
over directed graphs
2019 53rd Asilomar Conference on
Signals, Systems, and Computers
2019
arXiv
100 Years of Math Milestones
2019
Large Deviations for Products of
Non-Identically Distributed Network
Matrices With Applications to
Communication-Efficient Distributed
Learning and Inference
IEEE Transactions on Signal
Processing
2023
Inertial Projection Method for Solving
Monotone Operator Equations
2022 12th International Conference on
Information Science and Technology
(ICIST)
2022
Scientometric engineering: Exploring
citation dynamics via arXiv eprints
Quantitative Science Studies
2022
Large Deviations for Products of
Non-I.i.d. Stochastic Matrices with
Application to Distributed Detection
2018 IEEE International Symposium on
Information Theory (ISIT)
2018
Distributed sequence prediction: A
consensus+innovations approach
2016 IEEE Global Conference on Signal
and Information Processing
(GlobalSIP)
2016
Distributed generalized likelihood ratio
tests: Fundamental limits and tradeoffs
2016 IEEE International Conference on
Acoustics, Speech and Signal Processing
(ICASSP)
2016
Distributed Recursive Estimation under
Heavy-Tail Communication Noise
SIAM Journal on Control and
Optimization
2023
Preprint repository arXiv achieves
milestone million uploads
Physics Today
2014
Distributed recursive composite hypothesis
testing: Imperfect communication
2016 IEEE International Symposium on
Information Theory (ISIT)
2016
On Arxiv Moderation System
Unknown Venue
2023
Fine Tuning Auto Regressive LLMs for Long
Document Abstractive Summarization
2023 IEEE 2nd International Conference
on Industrial Electronics: Developments
& Applications (ICIDeA)
2023
Federated Representation Learning for
Automatic Speech Recognition
3rd Symposium on Security and Privacy
in Speech Communication
2023
Code2Drive: A Code-based Interactive and
Educational Driving Environment for
Improving the Youth Driving Learning and
Training using Machine Learning
Machine Learning &
Applications
2023
What Learned Representations and Influence
Functions Can Tell Us About Adversarial
Examples
Findings of the Association for
Computational Linguistics: IJCNLP-AACL
2023 (Findings)
2023
Learning When to Trust Which Teacher for
Weakly Supervised ASR
INTERSPEECH 2023
2023
Token Selection from Multiple Input Places
Asset Analytics
2023
Velocimeter LIDAR-Based Multiplicative
Extended Kalman Filter for Terrain
Relative Navigation App...
Unknown Venue
2022
Proceedings of the First Workshop on
Federated Learning for Natural Language
Processing (FL4NLP 2022)
Unknown Venue
2022
Optimization of Federated Learning
Communications with Heterogeneous
Quantization
2022 IEEE 22nd International Conference
on Communication Technology (ICCT)
2022
Optimization for Data-Driven Learning and
Control
Proceedings of the IEEE
2020
Distributed recursive testing of composite
hypothesis in multi-agent networks
Data Fusion in Wireless Sensor
Networks: A statistical signal
processing perspective
2019
Carnegie Mellon University
The Grants Register 2018
2018
Queue-based broadcast gossip algorithm for
consensus
2016 54th Annual Allerton Conference on
Communication, Control, and Computing
(Allerton)
2016
Attack Resilient Distributed Estimation: A
Consensus+Innovations Approach
2018 Annual American Control Conference
(ACC)
2018
Guest Editorial Inference and Learning
over Networks
IEEE Transactions on Signal and
Information Processing over
Networks
2016
Distributed Sequential Detection for
Gaussian Shift-in-Mean Hypothesis Testing
IEEE Transactions on Signal
Processing
2016
Distributed sequential detection for
Gaussian binary hypothesis testing:
Heterogeneous networks
2014 48th Asilomar Conference on
Signals, Systems and Computers
2014
Education
Carnegie Mellon University
PhD, Electrical and Computer Engineering / December, 2018
Pittsburgh, Pennsylvania, United
States of America
Experience
Amazon Services LLC
Senior Applied Scientist / October, 2020 — August, 2024
Bosch Center for Artificial Intelligence
Machine Learning Research Scientist / January, 2019 — October, 2020
GE Healthcare AI
Principal AI Scientist / August, 2024 — Present
Join Anit on NotedSource!
Join Now
At NotedSource, we believe that professors, post-docs, scientists and other researchers have deep, untapped knowledge and expertise that can be leveraged to drive innovation within companies. NotedSource is committed to bridging the gap between academia and industry by providing a platform for collaboration with industry and networking with other researchers.
For industry, NotedSource identifies the right academic experts in 24 hours to help organizations build and grow. With a platform of thousands of knowledgeable PhDs, scientists, and industry experts, NotedSource makes connecting and collaborating easy.
For academic researchers such as professors, post-docs, and Ph.D.s, NotedSource provides tools to discover and connect to your colleagues with messaging and news feeds, in addition to the opportunity to be paid for your collaboration with vetted partners.
Expert Institutions
Proudly trusted by
