In my research, I specialize in Online Learning with a dual focus, mainly exploring the theoretical novelties and practical applications within the Generative AI domain::

• Theoretical Novelties in Online Learning: My research delves into the foundational aspects of Online Learning. I focus on developing novel algorithms and providing rigorous theoretical guarantees, particularly in the context of multi-armed bandits, statistical learning theory, and cost-aware decision-making processes. Some of the key challenges I address include:
  • Algorithmic Efficiency: Designing algorithms that balance exploration and exploitation for optimal decision-making in dynamic and uncertain environments.
  • Theoretical Guarantees: Establishing convergence guarantees and performance bounds to ensure the robustness of these algorithms in various settings, such as fixed-confidence bandits and large-scale model evaluations.
• Applications in Generative AI: The second aspect of my research focuses on applying these theoretical advancements in the Generative AI space. I aim to optimize the performance and cost-efficiency of Large Language Models (LLMs) for various tasks. Key areas of application include:
  • Optimal LLM Selection: Developing methods to identify the most suitable LLM for a given task while minimizing computational and resource costs.
  • LLM Fine-tuning: Enhancing task-specific performance by fine-tuning LLMs with minimal resource use.
  • Prompt Optimization: Designing algorithms to discover the most effective prompts, ensuring the relevance and quality of the generated responses from LLMs.

Through this dual focus, my research bridges theory and practice, advancing Online Learning while innovating within the Generative AI landscape.

Past Works

Along with Online Learning, I previously worked in observational astronomy, focusing on the analysis of data from space archives. I mainly used two different approaches to explore various aspects of the universe:

• Statistical Analysis for Multiwavelength Astronomy: One aspect of my work involved delving into multiwavelength data, which encompasses a range of electromagnetic radiation, including X-rays, extending beyond what's visible. I used mathematical techniques to find hidden patterns and gain insights into a wide range of cosmic events and objects. This approach was particularly useful when I studied high-energy events and tried to confirm the existence of planets outside our solar system, known as exoplanets.
• Deep Learning with Astronomical Data: In addition to traditional statistical methods, I also employed advanced computer techniques like transformer models and attention mechanisms. These cutting-edge tools helped me make sense of complex data from space. With deep learning, I could extract intricate details from diverse datasets, improving our understanding of the physical processes that govern the universe. I applied this approach to delve into high-energy observations, providing deeper insights into phenomena like supernovae, gamma-ray bursts, and active galactic nuclei.

By combining statistical analysis and deep learning, I contributed to our expanding knowledge of the cosmos. I also tackled the challenges presented by the massive and varied datasets that astronomers deal with.