Aadharsh Aadhithya A

👋 Hello! I am a Grad student at UT Austin (ECE-DICE). I Completed my Bachelors in AI, from Amrita Vishwa Vidhyapeetham, Coimbatore. I am fascinated by the power of modelling natural systems ever since I was introduced to Newton’s Laws. I beleive that modelling systems gives us great power, which liberates us in some sense, to do what we intend to do with great conviction. So, here I am, on a quest to build intelligent systems that help us understand natural phenomenons and to push the frontiers of human knowldege.

My research areas were largely, Graph Processing, Data-Driven Model Discovery and AI applications in Healthcare. I have authored several publications in these areas, under the mentorship of Dr. K.P. Soman, during my undergrad. Currently, I am exploring methods to build trustworthy intelligent systems and with strong theoritical gaurentees.

I am an curious researcher , love writing, both technical or otherwise. In my free time I write poems in English and Tamizh, into Photography and Cricket as well. If you want to connect with me, Feel free to connect over LinkedIn or Email . For an Informal Interaction , I prefer Instagram.

selected publications

Prospects of NFMD for Power System Frequency and Amplitude Estimation

Aadharsh Aadhithya, Neethu Mohan, S Sachin Kumar, Soman K.P., and Prabhaharan. Poornachandran

7th IEEE International Conference on Recent Advances and Innovations in Engineering, 2023

Abs HTML

Power quality monitoring and parameter estima- tion are essential for the proper functioning of modern power grids. Various techniques have been proposed to estimate the characteristics of power signals and to gain insight into their dynamics. Non-stationary Fourier mode decomposition (NFMD) is a new interpretable time-frequency analysis framework for non-stationary and nonlinear signals. This work investigates the prospects of NFMD in the estimation of power-system characteristics such as fundamental frequency, amplitude and presence of disturbance components. Usage of NFMD as a noise removal technique is also explored in the current work. Results show that NFMD is robust to noisy disturbances and can perform well in noisy environments. The proposed methodology can be used for real-time analysis and interpretation of large volume of data from advanced smart metering techniques such as micro- phasor measurement units in microgrids
Learning (With) Distributed Optimization

Aadharsh Aadhithya, Abinesh S, Akshaya J, Jayanth M, Vishnu Radhakrishnan, Sowmya V, and Soman K. P

2023

Abs HTML

This paper provides an overview of the historical progression of distributed optimization techniques, tracing their development from early duality-based methods pioneered by Dantzig, Wolfe, and Benders in the 1960s to the emergence of the Augmented Lagrangian Alternating Direction Inexact Newton (ALADIN) algorithm. The initial focus on Lagrangian relaxation for convex problems and decomposition strategies led to the refinement of methods like the Alternating Direction Method of Multipliers (ADMM). The resurgence of interest in distributed optimization in the late 2000s, particularly in machine learning and imaging, demonstrated ADMM’s practical efficacy and its unifying potential. This overview also highlights the emergence of the proximal center method and its applications in diverse domains. Furthermore, the paper underscores the distinctive features of ALADIN, which offers convergence guarantees for non-convex scenarios without introducing auxiliary variables, differentiating it from traditional augmentation techniques. In essence, this work encapsulates the historical trajectory of distributed optimization and underscores the promising prospects of ALADIN in addressing non-convex optimization challenges.